© 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. 22203
    Prev
    Next
    INDEX
    Explanations

    location-related texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Yes
    -0.26
     vis
    -0.26
     visa
    -0.26
    éĹŃ
    -0.26
    tract
    -0.26
    纳æĸ¯
    -0.25
    velle
    -0.25
     vaz
    -0.25
    åĥµ
    -0.25
    <tbody
    -0.25
    POSITIVE LOGITS
    unami
    0.27
    人æīįåŁ¹åħ»
    0.27
     politics
    0.27
    inherits
    0.26
    .advance
    0.26
    ä¸įåıĹ
    0.26
    fan
    0.25
    Advance
    0.24
    herits
    0.24
    tip
    0.24
    Activations Density 0.023%

    No Known Activations