© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 40866
    Prev
    Next
    INDEX
    Explanations

    Frustration or failure

    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
    Negative Logits
     Loch
    -0.28
    quat
    -0.27
    欢è¿İæĤ¨
    -0.26
    ogle
    -0.26
     realise
    -0.25
    ivable
    -0.25
    /pages
    -0.24
    ree
    -0.24
    Possible
    -0.24
    roups
    -0.24
    POSITIVE LOGITS
    è¦ģçĶ¨
    0.31
    lle
    0.30
    åľ¨
    0.30
    base
    0.29
    -use
    0.29
    è¦ģåľ¨
    0.28
     Use
    0.28
    åŁºæķ°
    0.28
    mere
    0.27
    Use
    0.27
    Activations Density 0.002%

    No Known Activations