© 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. 25-TRANSCODER-HP
    7. 109386
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ´»è·ĥ
    -0.26
    eus
    -0.26
    çªģå¦Ĥåħ¶æĿ¥
    -0.26
     convenience
    -0.25
    kip
    -0.25
    eve
    -0.24
    tty
    -0.24
    çķĻè¨Ģ
    -0.24
    èµĮ
    -0.24
    digits
    -0.23
    POSITIVE LOGITS
    è··
    0.30
    对æĸ¹
    0.27
    ç«łç¨ĭ
    0.26
    åħ³åĪĩ
    0.25
    ombat
    0.25
    çĶ²æĸ¹
    0.24
     Classics
    0.24
    statt
    0.24
    -percent
    0.24
    wort
    0.24
    Activations Density 0.129%

    No Known Activations