© 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. 14-TRANSCODER-HP
    7. 40812
    Prev
    Next
    INDEX
    Explanations

    spe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pu
    -0.27
    æ²Ł
    -0.27
    éĶī
    -0.25
    osite
    -0.24
    æĿµ
    -0.24
    aps
    -0.24
    æĦŁ
    -0.23
    ãģĻãģIJ
    -0.23
     prof
    -0.23
     shot
    -0.23
    POSITIVE LOGITS
    åģļ大
    0.26
    olie
    0.25
    åĹī
    0.24
    羣æŃ£åģļåĪ°
    0.24
    åħ¶ä»ĸ人
    0.24
    vection
    0.24
    æ¯ı人
    0.24
    ynchronously
    0.24
    带ä¸Ĭ
    0.24
    ÑĢе
    0.24
    Activations Density 0.199%

    No Known Activations