© 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. 24-TRANSCODER-HP
    7. 151167
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mag
    -0.26
    felt
    -0.25
     Mellon
    -0.25
    ãĤĥ
    -0.25
     persisted
    -0.25
    icken
    -0.24
    æĮģä¹ħ
    -0.24
     darkest
    -0.24
    çĤ¼
    -0.23
    fest
    -0.23
    POSITIVE LOGITS
    iode
    0.28
     PARTICULAR
    0.27
    ä¸įå®ļ
    0.26
     particular
    0.26
     anecd
    0.25
    å®ĥåı¯ä»¥
    0.25
    aller
    0.25
     numerical
    0.25
    ä½Ĩå®ĥ
    0.25
     ÄijáºŃu
    0.24
    Activations Density 0.914%

    No Known Activations