© 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. 43505
    Prev
    Next
    INDEX
    Explanations

    0

    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
     sol
    -0.30
    izio
    -0.26
     quarter
    -0.26
    å°¸
    -0.26
    .Delay
    -0.26
    å¾Īå¤ļ人
    -0.25
    fte
    -0.25
    |M
    -0.24
    以ä¸Ĭ
    -0.24
    ammer
    -0.24
    POSITIVE LOGITS
    çĴ§
    0.29
    ishly
    0.28
    icals
    0.28
     stamps
    0.28
    uve
    0.28
    casts
    0.28
    gages
    0.28
    uco
    0.27
    structuring
    0.27
    +',
    0.27
    Activations Density 0.005%

    No Known Activations