© 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. 39024
    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
    åĪĨå¸ĥ
    -0.28
    åĪĨæķ°çº¿
    -0.27
    nee
    -0.27
    éĹ²
    -0.26
    åĪĨæķ£
    -0.26
    ÑĢин
    -0.25
    æī©æķ£
    -0.25
    &q
    -0.25
     Tee
    -0.25
     Sus
    -0.24
    POSITIVE LOGITS
     hostage
    0.28
    proper
    0.27
    edom
    0.27
    榻
    0.26
    ationally
    0.26
    awe
    0.26
    estar
    0.26
    anni
    0.26
     properly
    0.25
     proper
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.