© 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. 27-TRANSCODER-HP
    7. 58597
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    笼
    -0.29
     stro
    -0.27
    Atl
    -0.25
    éĽŀ
    -0.25
    æ¥Ń
    -0.25
    æĪIJéķ¿
    -0.24
    éĺľ
    -0.24
    cola
    -0.24
    çIJ°
    -0.24
     portrayed
    -0.23
    POSITIVE LOGITS
    åĭĭ
    0.27
    åħ¬åħ±æľįåĬ¡
    0.26
     honors
    0.25
     наÑģ
    0.25
    ..'
    0.24
    PAR
    0.24
     services
    0.24
    _sz
    0.24
    ìĦľë¹ĦìĬ¤
    0.23
     relationship
    0.23
    Activations Density 1.700%

    No Known Activations