© 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. 129945
    Prev
    Next
    INDEX
    Explanations

    quarry

    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
    让ä»ĸ
    -0.27
     Ihr
    -0.27
    让她
    -0.26
     compartment
    -0.25
    èģĶç½ij
    -0.25
    å±ķæ¼Ķ
    -0.24
    åĩºåħ¥å¢ĥ
    -0.24
     EXPRESS
    -0.24
    è®ĵä»ĸ
    -0.24
     ),↵↵
    -0.24
    POSITIVE LOGITS
    arily
    0.29
    aries
    0.27
    utos
    0.27
    å¹ķ
    0.26
    uble
    0.26
    æµģ
    0.26
    çĸ¾
    0.25
    raf
    0.25
    æ¸İ
    0.25
    atif
    0.25
    Activations Density 4.184%

    No Known Activations