© 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. 43819
    Prev
    Next
    INDEX
    Explanations

    very

    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
    æĽ³
    -0.25
    бол
    -0.25
    ivant
    -0.24
    æ°ijæĶ¿å±Ģ
    -0.24
    身为
    -0.23
    渥
    -0.23
    _abort
    -0.23
     Moto
    -0.23
     flaw
    -0.23
     BaseModel
    -0.23
    POSITIVE LOGITS
    大
    0.33
    urai
    0.31
     large
    0.30
     exc
    0.29
     Exc
    0.28
    _large
    0.28
     long
    0.27
    -exc
    0.27
     square
    0.26
     sum
    0.26
    Activations Density 0.000%

    No Known Activations