© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    对éĿ¢
    -0.25
     explanation
    -0.24
    sector
    -0.24
    åľ¨å½ĵåľ°
    -0.24
    è¿Ľåı£
    -0.23
    åĽ½å®¶å®īåħ¨
    -0.23
    fra
    -0.23
    bac
    -0.22
     Loc
    -0.22
    ulton
    -0.22
    POSITIVE LOGITS
    个人
    0.33
     personal
    0.29
    personal
    0.28
    icorn
    0.28
    åħ¨èĥ½
    0.28
    é¢Ħè¨Ģ
    0.26
    ĮĢ
    0.26
    inka
    0.25
    orb
    0.25
    -On
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.