© 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. 9-TRANSCODER-HP
    7. 30109
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icut
    -0.23
    por
    -0.23
    needle
    -0.22
    .gf
    -0.22
    alach
    -0.22
    åħ¨æĸĩ
    -0.22
    çľĭå¾Ĺ
    -0.21
    ayne
    -0.21
    es
    -0.21
    (cond
    -0.21
    POSITIVE LOGITS
     semp
    0.26
    rott
    0.26
     Synopsis
    0.25
    ambre
    0.23
     vicinity
    0.22
     możliwe
    0.22
    å¢Ļä¸Ĭ
    0.22
     zus
    0.22
     jes
    0.21
     avis
    0.21
    Activations Density 2.485%

    No Known Activations