© 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. 41571
    Prev
    Next
    INDEX
    Explanations

    temperature regulators

    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
    룸
    -0.28
    室åĨħ
    -0.26
    room
    -0.26
    nik
    -0.26
    net
    -0.25
    NET
    -0.25
    imos
    -0.24
    sequ
    -0.24
    atie
    -0.24
    otros
    -0.24
    POSITIVE LOGITS
     close
    0.32
    çļĦåIJĪä½ľ
    0.29
    çļĦæĵįä½ľ
    0.29
    -connected
    0.28
    -oper
    0.28
    æĵįä½ľ
    0.28
    -co
    0.28
    è¿ŀæİ¥
    0.28
    -close
    0.27
    OPER
    0.27
    Activations Density 0.002%

    No Known Activations