© 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. 162627
    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
    离
    -0.28
     Dental
    -0.27
     dental
    -0.27
    ç²¾åĵģ
    -0.26
    iel
    -0.26
     Clo
    -0.25
    .fac
    -0.25
    沫
    -0.25
    æ¿ł
    -0.25
    人大
    -0.25
    POSITIVE LOGITS
     tempted
    0.29
    bole
    0.28
    .getStatusCode
    0.28
     preferable
    0.26
    ombo
    0.26
    ouble
    0.25
    ubbo
    0.25
     StatusCode
    0.25
     sabotage
    0.24
    obox
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.