© 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. 35-TRANSCODER-HP
    7. 40749
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ote
    -0.35
    alty
    -0.33
    ality
    -0.30
    ments
    -0.30
    ilate
    -0.29
    olo
    -0.28
     fulfil
    -0.28
    ment
    -0.27
    ting
    -0.27
    ованиÑı
    -0.26
    POSITIVE LOGITS
    ahir
    0.36
    kah
    0.34
    mah
    0.32
     ah
    0.32
    -S
    0.32
    edImage
    0.31
     Ah
    0.31
     Herc
    0.30
    .CR
    0.30
     AH
    0.29
    Activations Density 1.180%

    No Known Activations