© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7985
    Prev
    Next
    INDEX
    Explanations

    hem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eto
    -0.31
    essional
    -0.29
    inear
    -0.28
    ä¹ĺ
    -0.27
    inal
    -0.26
    ongan
    -0.26
     multip
    -0.25
     closed
    -0.25
     NONINFRINGEMENT
    -0.25
    ifty
    -0.25
    POSITIVE LOGITS
    åŁĭ
    0.32
     remembers
    0.26
    éĵŃè®°
    0.25
    leurs
    0.25
    æģķ
    0.25
    éķ¿çŁŃ
    0.25
    èĨº
    0.25
    ÑģÑĥд
    0.24
    ä¼¼
    0.24
     remember
    0.24
    Activations Density 0.012%

    No Known Activations