© 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. 23-TRANSCODER-HP
    7. 24213
    Prev
    Next
    INDEX
    Explanations

    String fragments, possibly names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imest
    -0.27
    atra
    -0.26
    sus
    -0.24
    庶
    -0.24
    ivities
    -0.24
    -application
    -0.24
    åīįä¸ī
    -0.24
     utilisateur
    -0.23
    /win
    -0.23
    ÑģÑħ
    -0.23
    POSITIVE LOGITS
    ategic
    0.30
    lining
    0.30
    ategies
    0.27
    æĿ¾å¼Ľ
    0.27
    ency
    0.26
    agy
    0.26
    .format
    0.26
    .fromCharCode
    0.25
    /cgi
    0.25
    ict
    0.24
    Activations Density 0.257%

    No Known Activations