© 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. 63467
    Prev
    Next
    INDEX
    Explanations

    code

    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
    lav
    -0.30
     lax
    -0.25
    idf
    -0.24
    ä¸ķ
    -0.24
     Pref
    -0.24
    æ·ij
    -0.24
    loadModel
    -0.23
    å¤ı天
    -0.23
    RULE
    -0.23
    éŁ³ä¹IJä¼ļ
    -0.23
    POSITIVE LOGITS
    åī©ä½Ļ
    0.63
    åī©
    0.53
    remaining
    0.53
     remaining
    0.52
    åī©ä¸ĭçļĦ
    0.50
    _remaining
    0.49
    .remaining
    0.48
    åī©ä¸ĭ
    0.48
     leftover
    0.47
    Remaining
    0.46
    Activations Density 18.162%

    No Known Activations