© 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. 33-TRANSCODER-HP
    7. 54526
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sands
    -0.28
    ographically
    -0.27
     aud
    -0.26
     Sand
    -0.24
    ltr
    -0.24
    éŃĤ
    -0.24
    éĻ°
    -0.24
    éĿ¢
    -0.24
     POWER
    -0.24
    åħĪ导
    -0.24
    POSITIVE LOGITS
    pher
    0.27
    害
    0.26
    eting
    0.26
    epy
    0.26
     pageIndex
    0.26
    esy
    0.26
    é£Łæ¬²
    0.26
    uther
    0.25
    ETING
    0.25
    ersions
    0.25
    Activations Density 0.012%

    No Known Activations