© 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. 22-TRANSCODER-HP
    7. 98267
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.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·²ä¹ħ
    -0.28
    æī¿
    -0.27
    mart
    -0.27
    cott
    -0.27
    æĢ¨
    -0.26
    æľĢåŁºæľ¬çļĦ
    -0.26
    ÑĥÑī
    -0.25
    åĪİ
    -0.25
    æ¯ķ
    -0.25
    ä¸ŃåİŁ
    -0.24
    POSITIVE LOGITS
    ','',
    0.26
    ètre
    0.26
    acier
    0.24
    liner
    0.24
    \CMS
    0.24
    alars
    0.24
     IPs
    0.24
    IÃĬ
    0.24
    å·®çĤ¹
    0.24
     mapStateToProps
    0.23
    Activations Density 0.035%

    No Known Activations