© 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. 141465
    Prev
    Next
    INDEX
    Explanations

    (

    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
    æĺİçĻ½
    -0.26
    étude
    -0.26
    ceed
    -0.25
    ä¸ĭåıij
    -0.25
    å¸ĥå°Ķ
    -0.25
    ãĥĥãĥĪ
    -0.24
    åıĺå¼Ĥ
    -0.24
     wholes
    -0.24
     enqu
    -0.24
    erais
    -0.24
    POSITIVE LOGITS
    çļĤ
    0.30
    (hour
    0.27
    ledge
    0.25
    (outputs
    0.25
    atre
    0.24
    èķ¾
    0.24
    folios
    0.24
    ç®Ģ约
    0.24
    _inf
    0.23
    ä»¥ä¹łè¿ijå¹³
    0.23
    Activations Density 0.720%

    No Known Activations