© 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. 57805
    Prev
    Next
    INDEX
    Explanations

    able

    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
     chac
    -0.26
     rough
    -0.25
    кÑĥÑģ
    -0.25
     Submission
    -0.25
     haut
    -0.24
    éĨī
    -0.24
    åį°è±¡
    -0.24
    æ´¼
    -0.24
     ФедеÑĢ
    -0.24
    ä¸įä»ħè¦ģ
    -0.23
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.46
    ä»»ä½ķ人
    0.42
    ä»»ä½ķ
    0.41
     anymore
    0.38
     any
    0.37
    ä»»ä½ķå½¢å¼ı
    0.37
    æľīä»»ä½ķ
    0.37
     anywhere
    0.36
     anything
    0.35
    any
    0.34
    Activations Density 0.007%

    No Known Activations