© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40337
    Prev
    Next
    INDEX
    Explanations

    schools

    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
    Not in Any Lists

    No Comments

    Negative Logits
     elementary
    -0.34
     childhood
    -0.30
     obscure
    -0.28
    åħ¬åı¸
    -0.27
    ernal
    -0.27
     company
    -0.26
     advance
    -0.26
    à¸Ńม
    -0.25
     stationary
    -0.25
     central
    -0.25
    POSITIVE LOGITS
     AFC
    0.35
     APC
    0.34
     Genius
    0.33
     Britann
    0.32
     Mex
    0.31
     Hilton
    0.31
     Yuan
    0.31
     NTN
    0.30
     Mansion
    0.30
     McMahon
    0.30
    Activations Density 4.497%

    No Known Activations