© 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. 39398
    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
     amounts
    -0.27
     independence
    -0.26
     measures
    -0.26
     remaining
    -0.25
    oses
    -0.25
     initData
    -0.25
     attributes
    -0.25
     proportions
    -0.24
     growth
    -0.24
     ideals
    -0.24
    POSITIVE LOGITS
    è¿Ļ家åħ¬åı¸
    0.30
     Skywalker
    0.28
    èĻIJ
    0.27
     UNIX
    0.25
    äºıæįŁ
    0.25
    è´¶
    0.24
    æ¯Ļ
    0.24
    ä¹Łä¸įèĥ½
    0.24
    ighet
    0.24
     travers
    0.24
    Activations Density 1.186%

    No Known Activations

    This feature has no known activations.