© 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. 29528
    Prev
    Next
    INDEX
    Explanations

    hydro

    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
    è¡Ģ管
    -0.27
    Portal
    -0.27
    åĬŁèĥ½æĢ§
    -0.26
    ä¸īåĪĨ
    -0.26
    æļĤ
    -0.26
     Vict
    -0.26
     Races
    -0.25
    avar
    -0.25
    åĨįæĿ¥
    -0.24
    éĥİ
    -0.24
    POSITIVE LOGITS
    alom
    0.31
    ëij¥
    0.29
    eral
    0.27
     rowspan
    0.25
    åıijçİ°éĹ®é¢ĺ
    0.24
     publi
    0.24
    DSP
    0.24
    late
    0.24
     SPE
    0.24
    inged
    0.23
    Activations Density 3.082%

    No Known Activations