© 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. 32-TRANSCODER-HP
    7. 41824
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ottle
    -0.29
    еÑĢе
    -0.27
    (bb
    -0.26
    nosti
    -0.26
    ModifiedDate
    -0.26
    keit
    -0.26
    Ñĩе
    -0.26
    åĵģä½į
    -0.25
     lex
    -0.24
    ibble
    -0.24
    POSITIVE LOGITS
    nda
    0.26
    çIJ¶
    0.25
    *L
    0.25
    chap
    0.24
    次è¦ģ
    0.24
     Threads
    0.24
     Fork
    0.24
    igung
    0.24
    æ¿ł
    0.24
    rail
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.