© 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. 25-TRANSCODER-HP
    7. 109304
    Prev
    Next
    INDEX
    Explanations

    children

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĭİ
    -0.26
    lake
    -0.24
    <![
    -0.24
    isle
    -0.24
    :expr
    -0.23
    蹶
    -0.23
     Ñģнов
    -0.23
    åīįæľŁ
    -0.23
    å±į
    -0.23
    led
    -0.23
    POSITIVE LOGITS
    sam
    0.29
    mak
    0.26
     schools
    0.26
     conven
    0.25
    (||
    0.25
    mother
    0.24
    æľįè£ħ
    0.24
    GIN
    0.24
     ump
    0.24
    æ¯į
    0.24
    Activations Density 0.903%

    No Known Activations