© 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. 39137
    Prev
    Next
    INDEX
    Explanations

    say 'the ending -ers, -uses, -ures, -ies'

    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
     permits
    -0.34
     controls
    -0.30
     spawns
    -0.29
    æݧ
    -0.28
     returns
    -0.28
    controls
    -0.28
     tracks
    -0.28
     emits
    -0.27
     displays
    -0.26
    returns
    -0.26
    POSITIVE LOGITS
     con
    0.34
    ers
    0.33
    bases
    0.33
    nes
    0.29
    ides
    0.28
    ote
    0.28
    rie
    0.27
    qus
    0.26
    rones
    0.26
    ules
    0.26
    Activations Density 41.248%

    No Known Activations