© 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. 35-TRANSCODER-HP
    7. 39532
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    türk
    -0.33
     Åŀe
    -0.33
     türl
    -0.28
    sÅĤuch
    -0.28
    mız
    -0.28
     enr
    -0.28
    aÄŁa
    -0.28
    ÅŁeh
    -0.27
     learnt
    -0.27
    ömür
    -0.27
    POSITIVE LOGITS
    Ñĸ
    0.33
     Ã
    0.29
     èĭ¥è¦ģ
    0.27
    ÑĹ
    0.26
    Ãģ
    0.26
    ÃĴ
    0.25
    âģ
    0.25
    ÃĿ
    0.25
    ðĿĴ
    0.24
    ÑĬ
    0.24
    Activations Density 0.033%

    No Known Activations