© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57844
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽłä¸ºåľ¨
    -0.39
    because
    -0.36
    åĽłä¸º
    -0.35
    Because
    -0.35
    åĽłåľ°
    -0.34
     Because
    -0.30
    åĽłçĤº
    -0.30
    åĽłä¸ºä»ĸ们
    -0.30
     because
    -0.29
     porque
    -0.29
    POSITIVE LOGITS
     especially
    0.47
     particularly
    0.42
    å°¤åħ¶
    0.41
     Especially
    0.37
    å°¤åħ¶æĺ¯
    0.35
    especially
    0.34
     especialmente
    0.34
    çī¹åĪ«æĺ¯
    0.34
    particularly
    0.34
     Particularly
    0.33
    Activations Density 0.009%

    No Known Activations