© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149996
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļı
    -0.30
    ç«ĸ
    -0.28
     اÙĦØ£Ùħ
    -0.27
     delay
    -0.27
     term
    -0.26
    ÑģÑĥд
    -0.26
     Mack
    -0.25
    oz
    -0.25
     su
    -0.24
    亲
    -0.24
    POSITIVE LOGITS
    çĬĬ
    0.25
    çľ¼çķĮ
    0.25
    ält
    0.25
    åŀ¤
    0.25
    æĸ°éĻĪ
    0.25
     citizen
    0.25
    bull
    0.24
    禺
    0.24
    inja
    0.24
    ysql
    0.24
    Activations Density 0.442%

    No Known Activations

    This feature has no known activations.