© 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. 33-TRANSCODER-HP
    7. 53956
    Prev
    Next
    INDEX
    Explanations

    News commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -gap
    -0.30
    spiel
    -0.28
    icers
    -0.27
    rosso
    -0.27
    _gap
    -0.25
     TableRow
    -0.24
     tostring
    -0.24
    åıijå±ķæĸ¹åIJij
    -0.24
    _GAP
    -0.24
    è¿Ļä¹Īå¤ļ
    -0.24
    POSITIVE LOGITS
     ref
    0.32
     reporting
    0.29
     Of
    0.29
    ref
    0.29
    eff
    0.28
     completely
    0.28
     challenge
    0.27
     eff
    0.27
    of
    0.27
    )f
    0.26
    Activations Density 0.009%

    No Known Activations