© 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. 42858
    Prev
    Next
    INDEX
    Explanations

    climate

    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
    çݯå¢ĥ
    -0.34
     Environment
    -0.31
    Env
    -0.30
     Env
    -0.28
     Ec
    -0.28
    çĴ°å¢ĥ
    -0.28
     Ecology
    -0.28
    æ°ĶåĢĻ
    -0.27
    çĶŁæĢģ
    -0.27
    èģĶ
    -0.27
    POSITIVE LOGITS
     condition
    0.30
    icture
    0.29
    esty
    0.26
     regulating
    0.26
     thumb
    0.26
    çĶŁäº§åķĨ
    0.26
    stag
    0.26
     control
    0.25
     change
    0.25
     deg
    0.25
    Activations Density 0.003%

    No Known Activations