© 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. 12-TRANSCODER-HP
    7. 22173
    Prev
    Next
    INDEX
    Explanations

    Describing location or movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rita
    -0.28
    parsers
    -0.26
    æ¦ľ
    -0.25
    /MIT
    -0.25
    çªł
    -0.24
    atched
    -0.24
     rigged
    -0.24
    çĻ¾ç§ij
    -0.24
    IEnumerator
    -0.24
    .rdf
    -0.24
    POSITIVE LOGITS
    梦è§ģ
    0.31
    ivable
    0.30
    ooth
    0.29
     inc
    0.26
    [:
    0.25
    acci
    0.24
    oops
    0.24
    å¼¹
    0.24
    æĮģæľīçļĦ
    0.23
    åıijè§ī
    0.23
    Activations Density 0.001%

    No Known Activations