© 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. 24-TRANSCODER-HP
    7. 150092
    Prev
    Next
    INDEX
    Explanations

    Locations and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argon
    -0.27
    лÑij
    -0.26
    ramework
    -0.25
     Whilst
    -0.25
     Madame
    -0.25
    çĮ·
    -0.25
    ificial
    -0.25
    criptor
    -0.24
     ull
    -0.24
     ux
    -0.24
    POSITIVE LOGITS
     leftist
    0.27
     firefighter
    0.25
     property
    0.25
    filer
    0.24
    amos
    0.24
     OU
    0.24
    æıŃå¼Ģ
    0.24
    GER
    0.23
    á»ĩt
    0.23
    [left
    0.23
    Activations Density 1.075%

    No Known Activations