© 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. 57832
    Prev
    Next
    INDEX
    Explanations

    side

    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
     constraint
    -0.28
     Fair
    -0.28
     equ
    -0.27
    祸
    -0.25
     evaluation
    -0.25
    اÙĤ
    -0.24
     shaping
    -0.24
     graduating
    -0.24
     Lag
    -0.24
    atem
    -0.24
    POSITIVE LOGITS
    ä¸ĩæĪ·
    0.35
    acity
    0.26
    è·¬
    0.26
    rons
    0.26
    ertz
    0.25
    enza
    0.24
     Esk
    0.24
    cepts
    0.24
    ialect
    0.24
    ouns
    0.24
    Activations Density 0.226%

    No Known Activations