© 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. 52894
    Prev
    Next
    INDEX
    Explanations

    scour

    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
     sc
    -0.32
     Sc
    -0.28
    -sc
    -0.27
     whit
    -0.27
    ives
    -0.25
    çĸ¤
    -0.25
    InputModule
    -0.25
    Sc
    -0.25
    atri
    -0.25
    _sc
    -0.24
    POSITIVE LOGITS
    cant
    0.28
    gest
    0.28
    ya
    0.28
    db
    0.26
    çĨŁ
    0.26
    ba
    0.25
    ero
    0.25
    xdb
    0.25
    ctica
    0.25
    yun
    0.24
    Activations Density 0.007%

    No Known Activations