© 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. 141999
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     Setter
    -0.27
     Fix
    -0.26
     Shard
    -0.25
    rog
    -0.24
    \u
    -0.24
    ucker
    -0.23
    ainer
    -0.23
    ween
    -0.23
    :`
    -0.23
    ROP
    -0.23
    POSITIVE LOGITS
    éĴŀ
    0.28
    thetic
    0.27
     orders
    0.27
    éĤ®ä»¶
    0.27
     alphabet
    0.27
    æ¶İ
    0.26
    æĭ·
    0.26
    åĪ¶åĵģ
    0.25
     tape
    0.25
    ä¸ĭè¾¾
    0.25
    Activations Density 8.113%

    No Known Activations