© 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. 44056
    Prev
    Next
    INDEX
    Explanations

    attacks and episodes

    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
    çħ§
    -0.28
    ±Ð¾ÑĤ
    -0.28
    ãĤĤãĤĬ
    -0.27
    èĻij
    -0.26
    Path
    -0.25
     Dil
    -0.25
     Path
    -0.25
    -path
    -0.25
    (Path
    -0.25
    è¿Ļä¸Ģ
    -0.24
    POSITIVE LOGITS
    free
    0.34
     free
    0.33
    èĩªçĶ±
    0.32
     FREE
    0.32
    Free
    0.32
    _free
    0.31
     Free
    0.30
    /free
    0.29
    -free
    0.29
    游
    0.28
    Activations Density 0.003%

    No Known Activations