© 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. 25-TRANSCODER-HP
    7. 107617
    Prev
    Next
    INDEX
    Explanations

    length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chances
    -0.29
    vit
    -0.28
    _detach
    -0.27
     Ret
    -0.27
    ä¸ĢåŃĹ
    -0.27
     Cond
    -0.27
    æĹłå£°
    -0.26
    ç¨ĭ度
    -0.26
    indsight
    -0.26
    \Container
    -0.25
    POSITIVE LOGITS
    fcc
    0.28
    $_
    0.26
    å¸Ĥéķ¿
    0.25
     Arena
    0.25
    ables
    0.25
    eways
    0.23
     queen
    0.23
    wise
    0.23
    ablish
    0.23
    ening
    0.23
    Activations Density 1.235%

    No Known Activations