© 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. 107212
    Prev
    Next
    INDEX
    Explanations

    allows

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å®ĥåı¯ä»¥
    -0.33
     clearer
    -0.27
    èĸľ
    -0.26
    åķª
    -0.26
    è¿Ļçīĩ
    -0.25
    -hours
    -0.25
    æ·Ģ
    -0.24
    ax
    -0.24
    å®ĥ
    -0.24
    sville
    -0.24
    POSITIVE LOGITS
    ded
    0.28
     voluntarily
    0.28
     kra
    0.26
    bab
    0.26
    é¢IJ
    0.25
     arbitrarily
    0.25
    oor
    0.25
    otic
    0.24
     Editing
    0.24
     anywhere
    0.24
    Activations Density 0.934%

    No Known Activations