© 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. 9-TRANSCODER-HP
    7. 29806
    Prev
    Next
    INDEX
    Explanations

    legal/government institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŀ¢çº½
    -0.28
    tre
    -0.27
    ouncer
    -0.26
     zob
    -0.26
     feat
    -0.25
    åĪ¤å¤Ħ
    -0.25
    filer
    -0.25
     Henderson
    -0.25
    IID
    -0.25
     extents
    -0.24
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij
    0.27
    åħ±åĴĮåĽ½
    0.26
    éĹ®ä»ĸ
    0.26
    umen
    0.26
    uct
    0.25
    inen
    0.25
     Mun
    0.25
    æ¯ķä¸ļ
    0.24
    éĥ¨å§Ķ
    0.24
     nar
    0.24
    Activations Density 2.689%

    No Known Activations