© 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. 20-TRANSCODER-HP
    7. 63901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "\↵
    -0.25
    init
    -0.24
    _PARAMETER
    -0.23
    åıijå±ķéĺ¶æ®µ
    -0.23
     Init
    -0.23
    BEL
    -0.23
    atem
    -0.23
    è¿Ļ个æĹ¶ä»£
    -0.23
    寨
    -0.23
    èĬ¯
    -0.23
    POSITIVE LOGITS
    çĵ¶
    0.27
    è°¯
    0.26
     artillery
    0.25
     irresist
    0.25
    thon
    0.25
    åħ³åı£
    0.24
    pta
    0.24
    çĤ®
    0.24
    éļ¾å¿ĺ
    0.24
    è¹Ļ
    0.24
    Activations Density 18.846%

    No Known Activations

    This feature has no known activations.