© 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. 35-TRANSCODER-HP
    7. 40375
    Prev
    Next
    INDEX
    Explanations

    problems or errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    稳å®ļ
    -0.45
    稳å®ļçļĦ
    -0.40
    æŃ£ç¡®
    -0.39
    ç©©å®ļ
    -0.38
    ç¨³åĽº
    -0.35
    æŃ£ç¡®çļĦ
    -0.35
    :".$
    -0.35
    稳å®ļæĢ§
    -0.34
    (valid
    -0.33
    åIJĪçIJĨ
    -0.33
    POSITIVE LOGITS
     robbed
    0.37
     laz
    0.35
     peeled
    0.33
     hard
    0.33
     unavoid
    0.33
     irritating
    0.33
     inadvertently
    0.32
     afflicted
    0.32
     offending
    0.32
    被éªĹ
    0.32
    Activations Density 3.945%

    No Known Activations