© 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. 41270
    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
    ä¼ij
    -0.29
    reno
    -0.29
     Vacuum
    -0.28
     Afro
    -0.28
    çľŁç©º
    -0.27
    acea
    -0.25
     Datagram
    -0.25
    è§ĨåIJ¬
    -0.25
     lag
    -0.25
    èµĦ
    -0.25
    POSITIVE LOGITS
    eliness
    0.26
     inadvertently
    0.24
     underage
    0.24
     OP
    0.24
    ’un
    0.24
     ?↵
    0.23
    ’T
    0.23
    here
    0.23
     competition
    0.23
    èµİåĽŀ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.