© 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. 24-TRANSCODER-HP
    7. 149776
    Prev
    Next
    INDEX
    Explanations

    belief

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    骨骼
    -0.26
     mé
    -0.24
    agrid
    -0.24
    relay
    -0.24
     uneven
    -0.23
    recall
    -0.23
     vÃŃ
    -0.23
    ellow
    -0.23
    .poly
    -0.23
     Equip
    -0.22
    POSITIVE LOGITS
     herself
    0.27
    eful
    0.26
    _flutter
    0.24
    çĻ¾å¼º
    0.24
     propositions
    0.24
    -bel
    0.24
    åħ¨æĹ¥
    0.23
     frontier
    0.23
    -based
    0.23
    /pp
    0.23
    Activations Density 0.973%

    No Known Activations