© 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. 12-TRANSCODER-HP
    7. 23048
    Prev
    Next
    INDEX
    Explanations

    philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħįè´£
    -0.28
    webkit
    -0.25
     Gloss
    -0.25
    çĬ
    -0.25
     Cow
    -0.24
    -archive
    -0.24
    è¿İæĿ¥äºĨ
    -0.24
    /tos
    -0.24
    idge
    -0.24
    æīĭèīº
    -0.24
    POSITIVE LOGITS
    asti
    0.29
     outdoors
    0.29
    atem
    0.28
    篮
    0.28
    ilon
    0.27
    线ä¸ĭ
    0.27
    elts
    0.25
    ycz
    0.25
    itness
    0.25
    éĽ
    0.25
    Activations Density 0.009%

    No Known Activations