© 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. 40000
    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
     loc
    -0.31
    köp
    -0.30
    æľ¬èº«çļĦ
    -0.29
    ))==
    -0.28
    tré
    -0.27
    PropertyParams
    -0.27
    ysz
    -0.27
    éparation
    -0.27
    åĪĹ
    -0.27
     Column
    -0.27
    POSITIVE LOGITS
    å¯ĮåIJ«
    0.28
    åħ¶ä»ĸåĽ½å®¶
    0.27
     Celt
    0.27
    æķ°åŃĹè´§å¸ģ
    0.25
    åĽ½éĻħåIJĪä½ľ
    0.25
    ill
    0.24
     cougar
    0.24
     Wrath
    0.24
    åįģåĩłä¸ª
    0.24
    .organization
    0.23
    Activations Density 70.367%

    No Known Activations

    This feature has no known activations.