© 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. 35-TRANSCODER-HP
    7. 40411
    Prev
    Next
    INDEX
    Explanations

    ther

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dependency
    -0.31
    dependencies
    -0.28
    ampions
    -0.28
    å½±åĵįåĬĽ
    -0.25
    walking
    -0.25
    topl
    -0.25
    转åŀĭåıijå±ķ
    -0.25
    testing
    -0.24
    Analy
    -0.24
    tau
    -0.24
    POSITIVE LOGITS
    ita
    0.50
    cia
    0.38
    itas
    0.37
    isce
    0.35
    vit
    0.35
    ica
    0.33
    ice
    0.32
    ite
    0.32
    ico
    0.31
    иÑĤа
    0.31
    Activations Density 1.065%

    No Known Activations