© 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. 150394
    Prev
    Next
    INDEX
    Explanations

    Technical or code-related content

    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
    aneously
    -0.30
    æĺĻ
    -0.26
    ocio
    -0.26
    æĢĿç»´
    -0.25
     discipline
    -0.25
    çģ¾åĮº
    -0.25
    çĶĺèĤĥçľģ
    -0.25
     Vent
    -0.25
    çļĦä¼ĺçĤ¹
    -0.24
    .fig
    -0.24
    POSITIVE LOGITS
    aker
    0.30
    å§ij
    0.29
    itize
    0.28
    ucker
    0.28
     ton
    0.26
    ton
    0.25
    /I
    0.24
    ash
    0.24
    ropic
    0.24
    uem
    0.24
    Activations Density 0.094%

    No Known Activations