© 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. 57806
    Prev
    Next
    INDEX
    Explanations

    there

    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
     nothing
    -0.38
     no
    -0.37
    没æľī太大
    -0.34
    ä¸įä¼ļæľī
    -0.34
     kein
    -0.33
    ä¸įåŃĺåľ¨
    -0.32
     neither
    -0.32
    æĹł
    -0.32
    没ä»Ģä¹Ī
    -0.30
    没æľīä»»ä½ķ
    -0.30
    POSITIVE LOGITS
    ahoo
    0.27
    /respond
    0.27
    ALSE
    0.26
    ysize
    0.26
     Respond
    0.25
    edith
    0.25
    çĶ¸
    0.24
    pole
    0.24
     Calories
    0.24
    ãİľ
    0.24
    Activations Density 0.001%

    No Known Activations