© 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. 31-TRANSCODER-HP
    7. 18558
    Prev
    Next
    INDEX
    Explanations

    Technical and abstract language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸ®
    -0.29
     comb
    -0.29
    itations
    -0.28
     settles
    -0.27
    esk
    -0.27
    utter
    -0.26
     settle
    -0.26
    ourney
    -0.26
    UT
    -0.26
    ãĤ¤ãĥĪ
    -0.26
    POSITIVE LOGITS
    æ´»æĢ§
    0.26
    uada
    0.26
    åIJĥåĪ°
    0.24
    å¼Łå¼Ł
    0.24
    .rstrip
    0.23
     ACTIVE
    0.23
    æĸ¡
    0.23
    pass
    0.23
    å¼Ĭ
    0.23
    ChangedEventArgs
    0.23
    Activations Density 6.252%

    No Known Activations