© 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. 41234
    Prev
    Next
    INDEX
    Explanations

    the

    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
     conform
    -0.30
    eer
    -0.29
     adher
    -0.25
    äºĭæĥħ
    -0.25
    eken
    -0.25
    ä¿®
    -0.24
    éĩĩ
    -0.24
    ()?
    -0.24
    æī£
    -0.24
    次è¦ģ
    -0.24
    POSITIVE LOGITS
     redistributed
    0.28
    à°³
    0.27
     relieved
    0.26
     decoded
    0.25
    angelog
    0.24
    éŃĩ
    0.24
    缴èIJ¥
    0.24
    éĿ¢åŃIJ
    0.23
    iliated
    0.23
    æ¸IJæ¸IJ
    0.23
    Activations Density 0.116%

    No Known Activations