© 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. 33-TRANSCODER-HP
    7. 53540
    Prev
    Next
    INDEX
    Explanations

    former

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ®ĸæ°ij
    -0.36
    æĸĩåĮĸéģĹ产
    -0.31
     colon
    -0.29
    sequence
    -0.28
     sequence
    -0.28
    触åıĬ
    -0.27
     colonial
    -0.26
    wer
    -0.26
     colonies
    -0.26
    weed
    -0.26
    POSITIVE LOGITS
    对åħ¬åı¸
    0.32
     Company
    0.29
    ông
    0.28
     chaud
    0.27
    Company
    0.27
    company
    0.26
    åħ¬åı¸çļĦ
    0.26
     company
    0.26
    -company
    0.26
    (company
    0.25
    Activations Density 0.009%

    No Known Activations