© 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. 54084
    Prev
    Next
    INDEX
    Explanations

    Code, files, and some text

    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
    UGH
    -0.29
    adge
    -0.27
    éĺ¿éĩĮ
    -0.27
    ombat
    -0.26
    minate
    -0.26
    ture
    -0.26
    hibit
    -0.26
    ãĤ¢ãĥ³
    -0.24
    ä¿¡
    -0.24
     Touch
    -0.24
    POSITIVE LOGITS
     sher
    0.31
    ichel
    0.29
    _pe
    0.28
    Principal
    0.28
    -pe
    0.27
    åŁºéĩij管çIJĨ
    0.27
    åĵģç±»
    0.26
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    0.25
    ographer
    0.24
    æĬ¥
    0.24
    Activations Density 0.004%

    No Known Activations