© 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. 27-TRANSCODER-HP
    7. 57272
    Prev
    Next
    INDEX
    Explanations

    disorganized information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rejected
    -0.30
    .reject
    -0.27
     defeat
    -0.27
    $MESS
    -0.27
    iale
    -0.26
    æĮ«æĬĺ
    -0.26
     rejection
    -0.25
    atre
    -0.25
     eins
    -0.25
     rejects
    -0.25
    POSITIVE LOGITS
     sense
    0.26
    æĿĥéĩį
    0.25
    ä¿ĥ
    0.25
     Wak
    0.25
     privilege
    0.25
    ç«¥
    0.24
    pel
    0.24
    æ³·
    0.24
    åºĶåĬĽ
    0.24
    æĽĿ
    0.23
    Activations Density 0.001%

    No Known Activations