© 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. 43041
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    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
    æ¯Ĵ
    -0.26
    è¿Ľä¸ĢæŃ¥
    -0.25
    ROOM
    -0.25
    rooms
    -0.25
     roomId
    -0.25
     rooms
    -0.24
    室
    -0.24
    eni
    -0.24
    ethe
    -0.23
     cuid
    -0.23
    POSITIVE LOGITS
    éĹ´çļĦ
    0.30
    rw
    0.28
    å®Ĺ
    0.26
     rw
    0.25
    filt
    0.25
    idge
    0.24
     stil
    0.24
    å®ĹæŨ
    0.24
    éĹ´
    0.24
    ADI
    0.24
    Activations Density 0.002%

    No Known Activations