© 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. 42620
    Prev
    Next
    INDEX
    Explanations

    paragraph

    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
    åŀĭä¼ģä¸ļ
    -0.33
    åľºæ¯ĶèµĽ
    -0.26
    wort
    -0.25
    erable
    -0.25
     Rid
    -0.25
     Callable
    -0.25
    CLR
    -0.25
     surrender
    -0.24
    ordinator
    -0.24
    主æĴŃ
    -0.24
    POSITIVE LOGITS
    åĨĻ
    0.39
    寫
    0.38
    æĴ°åĨĻ
    0.37
     write
    0.35
     writing
    0.35
    æĴ°
    0.33
     writ
    0.32
     Write
    0.31
     writes
    0.31
    åĨĻäºĨ
    0.31
    Activations Density 0.001%

    No Known Activations