© 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. 35-TRANSCODER-HP
    7. 39928
    Prev
    Next
    INDEX
    Explanations

    Service

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defending
    -0.26
     few
    -0.25
     omega
    -0.25
    åħ±åIJĮ
    -0.25
     attend
    -0.25
    urchase
    -0.24
    woo
    -0.24
     Reg
    -0.24
     Few
    -0.23
    è¶Ĭå¤ļ
    -0.23
    POSITIVE LOGITS
     IService
    0.35
     Service
    0.33
    æľįåĬ¡
    0.33
    	Service
    0.32
    plx
    0.31
    Service
    0.31
     service
    0.31
    çļĦæľįåĬ¡
    0.30
    .Service
    0.30
    _SERVICE
    0.29
    Activations Density 10.320%

    No Known Activations