© 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. 27-TRANSCODER-HP
    7. 57826
    Prev
    Next
    INDEX
    Explanations

    well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |[
    -0.30
    æŃ£åĢ¼
    -0.26
    ael
    -0.26
    iors
    -0.25
    å·²ä¹ħ
    -0.25
    duct
    -0.24
     Biography
    -0.23
    åĭŁ
    -0.23
    еÑģÑĤв
    -0.23
    âĸ¿
    -0.23
    POSITIVE LOGITS
     let
    0.33
    okin
    0.29
    让
    0.29
    lets
    0.28
     lets
    0.28
    _aliases
    0.28
    让æĪij
    0.28
     okay
    0.27
    è®©ä½ł
    0.27
    好åĥı
    0.26
    Activations Density 0.009%

    No Known Activations