© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     placeholders
    -0.27
    ä¸Ģ个èģĮä¸ļ
    -0.27
     logically
    -0.27
     identities
    -0.26
     probabilities
    -0.26
     redund
    -0.26
     homelessness
    -0.25
     unnecessarily
    -0.25
     physically
    -0.25
     hÃłnh
    -0.25
    POSITIVE LOGITS
    raw
    0.35
    com
    0.34
    op
    0.33
    agar
    0.33
    auto
    0.33
    pub
    0.31
    abs
    0.31
    ap
    0.30
    org
    0.30
    ent
    0.30
    Activations Density 2.545%

    No Known Activations

    This feature has no known activations.