© 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. 52812
    Prev
    Next
    INDEX
    Explanations

    technical and academic contexts

    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
    iable
    -0.25
     incumbent
    -0.25
    -pres
    -0.24
     phy
    -0.24
    -sur
    -0.24
    WillAppear
    -0.24
     Presidency
    -0.24
    éĨĴäºĨ
    -0.23
    å®Ľ
    -0.23
     Phy
    -0.23
    POSITIVE LOGITS
     determin
    0.33
    array
    0.31
    ym
    0.30
     Determin
    0.28
    fsp
    0.28
    ä¸įåĪ©
    0.28
     scale
    0.28
     array
    0.27
    å°º
    0.26
    brid
    0.26
    Activations Density 0.034%

    No Known Activations