© 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. 43542
    Prev
    Next
    INDEX
    Explanations

    is/are

    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
    swith
    -0.32
    sWith
    -0.28
    enheim
    -0.27
    Ñģал
    -0.26
    WithString
    -0.26
    WithError
    -0.26
    åij¼åĴĮ
    -0.25
    WithName
    -0.25
    wn
    -0.24
    urf
    -0.24
    POSITIVE LOGITS
     work
    0.35
    çķ¸
    0.32
    å·¥ä½ľ
    0.31
     working
    0.30
     hard
    0.30
     works
    0.29
    硬
    0.28
     promoting
    0.28
     leading
    0.28
    into
    0.28
    Activations Density 0.008%

    No Known Activations