© 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. 39605
    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
    :
    -0.39
    ,
    -0.38
    O
    -0.37
    ↵
    -0.36
    D
    -0.36
    d
    -0.36
    m
    -0.36
    A
    -0.35
    o
    -0.35
     m
    -0.35
    POSITIVE LOGITS
    ESA
    0.28
     sondern
    0.28
    ÑģÑĤвие
    0.27
    æīĢ以ä»ĸ
    0.27
    благо
    0.27
    EndInit
    0.26
    intérêt
    0.26
    ligt
    0.26
    ETCH
    0.26
    交æµģåIJĪä½ľ
    0.26
    Activations Density 3.500%

    No Known Activations

    This feature has no known activations.