© 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. 30-TRANSCODER-HP
    7. 94956
    Prev
    Next
    INDEX
    Explanations

    Corrupted technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    anka
    -0.29
    mitt
    -0.26
     Void
    -0.25
    redi
    -0.25
     crossed
    -0.24
     Hook
    -0.24
    Yet
    -0.24
     Yet
    -0.24
     burden
    -0.24
    @student
    -0.24
    POSITIVE LOGITS
    noDB
    0.26
    éļľ
    0.26
    latable
    0.24
    æĮĤåı·
    0.24
     shaping
    0.24
    èIJ½
    0.24
    ader
    0.23
    ensive
    0.23
    ady
    0.23
    _SHAPE
    0.23
    Activations Density 0.027%

    No Known Activations