© 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. 23-TRANSCODER-HP
    7. 23750
    Prev
    Next
    INDEX
    Explanations

    trail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rieg
    -0.28
    URN
    -0.27
    éĺĻ
    -0.25
    çĭ®
    -0.24
    麻éĨī
    -0.24
    urn
    -0.24
    .lazy
    -0.24
     Essays
    -0.23
     Affairs
    -0.23
     TMPro
    -0.23
    POSITIVE LOGITS
    worthy
    0.28
    äºĨèĩªå·±çļĦ
    0.28
    è¿Ļæīįæĺ¯
    0.28
    setter
    0.27
    led
    0.26
    odus
    0.26
     antid
    0.26
     scars
    0.25
    .githubusercontent
    0.25
    amm
    0.25
    Activations Density 0.455%

    No Known Activations