© 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. 39854
    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
    éĬ®
    -0.29
     dirs
    -0.26
    æ³ł
    -0.24
     directories
    -0.24
    NOWLED
    -0.24
    çİ
    -0.23
    缮å½ķ
    -0.23
     folders
    -0.23
    directive
    -0.23
    Folders
    -0.23
    POSITIVE LOGITS
     HttpMethod
    0.30
    ä¸įèµ·
    0.28
    -dis
    0.26
    åĬ¨éĿĻ
    0.26
     Dis
    0.25
    è¿Ļåıª
    0.25
    iris
    0.25
    TickCount
    0.25
    atto
    0.25
    åĢ¼çıŃ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.