© 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. 150299
    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
    空çĻ½
    -0.26
    olon
    -0.24
    isma
    -0.24
    æį¢
    -0.24
    argas
    -0.24
    antine
    -0.23
    ÑĥÑģ
    -0.23
    OKEN
    -0.23
    Inputs
    -0.23
    dup
    -0.22
    POSITIVE LOGITS
    åĩºçİ°éĹ®é¢ĺ
    0.27
     dozen
    0.25
    æĸ°éĽ¶åĶ®
    0.25
    ↵ ↵
    0.24
    éĿŀ常éĩįè¦ģ
    0.23
     auss
    0.23
    贯穿
    0.23
    è¯ģåĪ¸äº¤æĺĵ
    0.23
     ìŀĪ기
    0.23
    &M
    0.22
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.