© 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. 22730
    Prev
    Next
    INDEX
    Explanations

    jail

    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
     allotted
    -0.29
    sworth
    -0.28
    ç½ij讯
    -0.28
     fiat
    -0.25
    eson
    -0.24
    tera
    -0.24
    第ä¸īèĢħ
    -0.24
    tabpanel
    -0.24
     unlucky
    -0.24
     eu
    -0.24
    POSITIVE LOGITS
     magn
    0.29
    éĿĻéĿĻ
    0.28
     ups
    0.27
    åīįåĩłå¤©
    0.26
    éĿĻéĿĻåľ°
    0.26
    Magn
    0.25
    æĿijåħļæĶ¯éĥ¨
    0.25
    è±Į
    0.25
    åIJŀ
    0.24
    chan
    0.24
    Activations Density 0.005%

    No Known Activations