© 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. 107180
    Prev
    Next
    INDEX
    Explanations

    bl

    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
    aac
    -0.30
    å¸ħ
    -0.26
     Decompiled
    -0.25
     par
    -0.24
    acock
    -0.24
    pendicular
    -0.24
     exception
    -0.24
    ç°§
    -0.23
    宫
    -0.23
    ÅŁtır
    -0.23
    POSITIVE LOGITS
    gos
    0.26
    .Xr
    0.25
    /bl
    0.25
    ernaut
    0.25
    uetooth
    0.24
    ursday
    0.24
     Unique
    0.24
    лад
    0.23
    blah
    0.23
    azing
    0.23
    Activations Density 1.194%

    No Known Activations