© 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. 90025
    Prev
    Next
    INDEX
    Explanations

    Numbers and symbols

    np_max-act · gemini-2.0-flash
    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
    logan
    -0.28
    æĬĦ
    -0.26
    atively
    -0.26
    æ¹
    -0.26
    utron
    -0.25
    å°½åı¯èĥ½
    -0.25
    -Americ
    -0.25
    umber
    -0.24
    æ·±åħ¥äººå¿ĥ
    -0.24
    ITIVE
    -0.24
    POSITIVE LOGITS
     crit
    0.28
    âī§
    0.28
    lux
    0.26
    ä»»ä½ķ人
    0.26
    ohn
    0.26
    pell
    0.25
     Giles
    0.25
     involvement
    0.25
    clerosis
    0.25
    either
    0.24
    Activations Density 33.798%

    No Known Activations