© 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. 31-TRANSCODER-HP
    7. 18245
    Prev
    Next
    INDEX
    Explanations

    Despite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    breaker
    -0.29
    æľĢåıĹ
    -0.28
    å¾Ĺå¾Ī
    -0.27
     yourselves
    -0.26
    æīĵæī®
    -0.26
    è¡Į为
    -0.26
    æ°Ķæģ¯
    -0.26
    çľĭäºĨä¸Ģ
    -0.24
    æľĢ容æĺĵ
    -0.24
     getMax
    -0.24
    POSITIVE LOGITS
     this
    0.40
     our
    0.37
     continued
    0.35
     these
    0.33
     the
    0.32
     repeated
    0.32
     heavy
    0.32
     endless
    0.32
     its
    0.31
     today
    0.31
    Activations Density 0.025%

    No Known Activations