© 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. 150519
    Prev
    Next
    INDEX
    Explanations

    making choices/decisions

    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
    ä»Ģä¹Īåľ°æĸ¹
    -0.26
    succ
    -0.26
    empt
    -0.25
     cứ
    -0.25
    åıijè´¢
    -0.24
    åĮºåĿĹ
    -0.24
    .Entry
    -0.24
     succ
    -0.24
    ä¸Ģåij³
    -0.24
    мин
    -0.24
    POSITIVE LOGITS
    orado
    0.29
     decisions
    0.26
    ekt
    0.26
    _locator
    0.26
     décision
    0.26
    EDIATE
    0.24
     Tage
    0.24
    -guid
    0.24
    第äºĮ天
    0.24
     lifes
    0.24
    Activations Density 0.315%

    No Known Activations