© 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. 39047
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oo
    -0.36
    oon
    -0.36
    ooo
    -0.35
     Boeh
    -0.31
    vo
    -0.30
    Bo
    -0.30
    bo
    -0.30
    boo
    -0.29
    oooo
    -0.28
     Learned
    -0.28
    POSITIVE LOGITS
    halten
    0.30
    hani
    0.29
    hud
    0.29
    chal
    0.28
    hay
    0.27
    å¹³æŶ
    0.27
    rac
    0.27
    rÃŃ
    0.26
    hed
    0.26
    hazi
    0.26
    Activations Density 13.583%

    No Known Activations

    This feature has no known activations.