© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96777
    Prev
    Next
    INDEX
    Explanations

    be

    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
    缸åħ³åĨħ容
    -0.26
    沫
    -0.26
    _Email
    -0.26
    å¼ĢäºĨ
    -0.26
    .opend
    -0.26
    Sci
    -0.25
    åĬŁè¯¾
    -0.25
    客æĪ·éľĢæ±Ĥ
    -0.25
    evin
    -0.25
    sci
    -0.25
    POSITIVE LOGITS
     creative
    0.28
    \/\/
    0.27
    èĶ»
    0.26
     rid
    0.26
     careful
    0.26
    дÑĢа
    0.26
     Sure
    0.25
     th
    0.25
    ctic
    0.25
     sure
    0.25
    Activations Density 0.886%

    No Known Activations