© 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. 8635
    Prev
    Next
    INDEX
    Explanations

    has

    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
     thereof
    -0.29
    ªĮ
    -0.26
    æĹ¢
    -0.26
    çĻ¾åIJĪ
    -0.26
    ä¸ī级
    -0.25
    åľ¨åŃ¦æł¡
    -0.24
    REMOTE
    -0.24
    lsx
    -0.24
     ratified
    -0.23
    essages
    -0.23
    POSITIVE LOGITS
     Fre
    0.30
    广大å¸Ĥæ°ij
    0.29
    /cs
    0.27
    æ¶ī
    0.27
     liberty
    0.27
     fre
    0.26
    ncy
    0.25
     cheats
    0.25
     opp
    0.25
    巨大
    0.25
    Activations Density 0.006%

    No Known Activations