© 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. 107408
    Prev
    Next
    INDEX
    Explanations

    cre

    np_max-act · gemini-2.0-flash
    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
     self
    -0.28
     compte
    -0.27
    eds
    -0.27
    Self
    -0.27
     anchor
    -0.26
     bridge
    -0.26
     Self
    -0.26
     intercept
    -0.26
    çļ±çº¹
    -0.25
    ers
    -0.25
    POSITIVE LOGITS
    ·»
    0.32
    éĹ®æĪij
    0.30
    ä¸ĩåħĥ以ä¸Ĭ
    0.30
    å¦Ĥæŀľä½łæĥ³
    0.27
    ä¸ĩ家
    0.27
    -question
    0.26
    Otherwise
    0.26
    _TYP
    0.26
    çķĻä¸ĭæĿ¥
    0.26
    ToOne
    0.25
    Activations Density 0.874%

    No Known Activations