© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96765
    Prev
    Next
    INDEX
    Explanations

    relating to "turn"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iedade
    -0.29
     steam
    -0.29
    宾
    -0.28
    rown
    -0.27
    sm
    -0.27
    æ·¦
    -0.25
    cion
    -0.25
    rowing
    -0.25
     ÑģÑĤеп
    -0.25
     Mime
    -0.24
    POSITIVE LOGITS
     turns
    1.07
     turn
    1.00
    turn
    1.00
    -turn
    0.95
    Turn
    0.94
     Turns
    0.91
     Turn
    0.90
    _turn
    0.89
    .turn
    0.86
     turned
    0.81
    Activations Density 0.937%

    No Known Activations