© 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. 57635
    Prev
    Next
    INDEX
    Explanations

    Which one to use

    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
     prevalent
    -0.29
    æīĢ
    -0.27
    æīĢåģļçļĦ
    -0.27
     Popular
    -0.26
    ç¦Ħ
    -0.26
    æĮģæľīçļĦ
    -0.26
    rig
    -0.25
    åħ¶æīĢ
    -0.25
     sponsors
    -0.25
    cum
    -0.24
    POSITIVE LOGITS
    åıijéħµ
    0.36
    åŃ³
    0.28
     fitted
    0.27
    éĢĤ
    0.26
    æĽ´éĢĤåIJĪ
    0.26
    BBC
    0.25
    issing
    0.25
    æĹ¢æĺ¯
    0.24
    -UA
    0.24
     Uncategorized
    0.24
    Activations Density 0.004%

    No Known Activations