© 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. 32-TRANSCODER-HP
    7. 41460
    Prev
    Next
    INDEX
    Explanations

    Code and filenames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enge
    -0.28
     trab
    -0.28
    angle
    -0.26
    igli
    -0.26
    hos
    -0.26
    igue
    -0.25
    (angle
    -0.25
     sublist
    -0.25
    xes
    -0.24
    .fil
    -0.24
    POSITIVE LOGITS
    æķĸ
    0.29
    cour
    0.29
    ä¹ī
    0.27
    æ¼ı
    0.27
    ä¿Ħ
    0.26
    ADVERTISEMENT
    0.26
    常åĬ¡
    0.25
    èĢ³è¾¹
    0.24
    KY
    0.24
    pector
    0.24
    Activations Density 0.000%

    No Known Activations