© 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. 18-TRANSCODER-HP
    7. 90035
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°ģ
    -0.32
    always
    -0.29
    иÑĢов
    -0.28
    è§ģ
    -0.28
     always
    -0.28
     impro
    -0.27
    è¦ĭ
    -0.27
     pump
    -0.26
     sealed
    -0.26
    å§ĭç»Ī
    -0.25
    POSITIVE LOGITS
    å±ī
    0.28
    comma
    0.27
    verts
    0.26
    olo
    0.26
    éĢĴ
    0.26
    uele
    0.25
     Politico
    0.25
    antas
    0.25
    endum
    0.24
    æ¿ł
    0.24
    Activations Density 0.196%

    No Known Activations

    This feature has no known activations.