© 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. 40058
    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
     pneum
    -0.25
     Raz
    -0.25
    baugh
    -0.24
    IRR
    -0.23
     pier
    -0.23
    æ®Ĭ
    -0.23
     Buzz
    -0.23
    èĪŁ
    -0.23
    .codes
    -0.23
     exited
    -0.23
    POSITIVE LOGITS
    modx
    0.26
    åħ¶ä»ĸçݩ家
    0.24
    rove
    0.24
    SWEP
    0.24
    缸åºĶçļĦ
    0.24
    ä¸Ģ个人
    0.24
    è½®åĽŀ
    0.23
    ï¬ģ
    0.23
    å¾Īæ¸ħæ¥ļ
    0.23
    æ¯ı个人çļĦ
    0.23
    Activations Density 67.250%

    No Known Activations

    This feature has no known activations.