© 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. 24-TRANSCODER-HP
    7. 149436
    Prev
    Next
    INDEX
    Explanations

    Foreign language fragments

    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
     waiting
    -0.29
    AdapterFactory
    -0.28
     interviewing
    -0.28
     saying
    -0.27
     Saying
    -0.26
    çŃīå¾ħ
    -0.26
    strings
    -0.26
    让èĩªå·±
    -0.26
    _named
    -0.25
     waits
    -0.24
    POSITIVE LOGITS
    精度
    0.27
    leh
    0.26
     Britt
    0.25
     failure
    0.24
     Failure
    0.24
    æŁ°
    0.24
    ange
    0.23
    itect
    0.23
    建çŃijå·¥ç¨ĭ
    0.23
    æºı
    0.23
    Activations Density 0.455%

    No Known Activations