© 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. 43265
    Prev
    Next
    INDEX
    Explanations

    amazing/incredible

    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
    å°¤åħ¶
    -0.28
    尤为
    -0.28
    åĵªå®¶
    -0.28
    ä¸ĩåįĥ
    -0.26
    ing
    -0.26
    inned
    -0.26
    asured
    -0.26
    quired
    -0.26
     asked
    -0.26
    å¦ĤæѤ
    -0.25
    POSITIVE LOGITS
    ness
    0.41
    ly
    0.40
    NESS
    0.34
    LY
    0.34
    mente
    0.32
     finding
    0.30
    ä¸įè¿ĩ
    0.29
    izzo
    0.29
    оÑģÑĤи
    0.28
    оÑģÑĤÑĮ
    0.28
    Activations Density 0.010%

    No Known Activations