© 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. 43382
    Prev
    Next
    INDEX
    Explanations

    epis/epit

    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
    ebin
    -0.29
    ea
    -0.28
    yw
    -0.27
    antz
    -0.27
    edin
    -0.26
    eo
    -0.26
    ed
    -0.25
    å²IJ
    -0.25
    YST
    -0.25
    agy
    -0.25
    POSITIVE LOGITS
    å¸ĺ
    0.27
    èĦ±
    0.27
    opic
    0.26
    èľĥ
    0.26
    è£ħçĶ²
    0.26
    ç®Ķ
    0.26
    contre
    0.25
    odes
    0.25
     tác
    0.25
    夹
    0.24
    Activations Density 0.002%

    No Known Activations