© 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. 95055
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    sez
    -0.45
    se
    -0.44
    SES
    -0.43
    sem
    -0.41
    SEN
    -0.37
    pez
    -0.37
    SE
    -0.35
    SED
    -0.35
    ÂŃs
    -0.34
    sey
    -0.34
    POSITIVE LOGITS
    ated
    0.31
    åĩŃ
    0.28
    egrity
    0.28
    zÄħd
    0.27
    ereal
    0.27
    entrant
    0.26
    radi
    0.26
    NG
    0.25
    endum
    0.25
     itemView
    0.24
    Activations Density 0.992%

    No Known Activations