© 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. 107040
    Prev
    Next
    INDEX
    Explanations

    Classifications and disorders

    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
    çī©
    -0.26
    igen
    -0.26
     bếp
    -0.26
    essa
    -0.25
     Brill
    -0.25
    è£ģåĪ¤
    -0.25
    kte
    -0.25
    illin
    -0.24
    olt
    -0.24
    mites
    -0.24
    POSITIVE LOGITS
     Ñģнов
    0.28
    æ·Ģ
    0.26
    SWG
    0.26
    Coming
    0.24
     flank
    0.24
    å¤Ħåľ¨
    0.23
     hon
    0.23
    ç»ı常
    0.23
    Stop
    0.23
     Authors
    0.23
    Activations Density 0.892%

    No Known Activations