© 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. 58156
    Prev
    Next
    INDEX
    Explanations

    w

    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
    åĽłä¸ºå®ĥ
    -0.29
    ÑģÑĥд
    -0.26
    ç±³å°Ķ
    -0.26
    hr
    -0.24
    NORMAL
    -0.24
     ÑģообÑī
    -0.24
    hä
    -0.24
    人ãĤĤ
    -0.23
     RootState
    -0.23
    haus
    -0.23
    POSITIVE LOGITS
    anted
    0.31
    inkel
    0.30
    礼
    0.29
    elry
    0.27
    éĤ£äºĽ
    0.27
    ties
    0.26
    inder
    0.24
     ↵↵
    0.24
    sw
    0.24
    etta
    0.24
    Activations Density 0.008%

    No Known Activations