© 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. 30-TRANSCODER-HP
    7. 95788
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİ©
    -0.26
    åĨĪ
    -0.26
    uggy
    -0.25
     Exterior
    -0.25
    avr
    -0.25
     Unreal
    -0.25
     Ex
    -0.25
    mö
    -0.24
    irk
    -0.24
     frag
    -0.23
    POSITIVE LOGITS
    åıĹçģ¾
    0.30
    sector
    0.28
    Responder
    0.27
     disp
    0.26
    fw
    0.26
    embr
    0.25
     sector
    0.25
    ancias
    0.25
    )}.
    0.25
     dispens
    0.24
    Activations Density 0.002%

    No Known Activations