© 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. 27-TRANSCODER-HP
    7. 57321
    Prev
    Next
    INDEX
    Explanations

    software and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİŁæłĩé¢ĺ
    -0.30
    æİĤ
    -0.26
    磫
    -0.26
    alsy
    -0.25
     jap
    -0.24
     japan
    -0.24
    _before
    -0.23
     weighing
    -0.23
    ujet
    -0.23
    ellig
    -0.23
    POSITIVE LOGITS
    ç¬¬åĽĽ
    0.81
    第äºĶ
    0.80
    第
    0.77
     fifth
    0.76
    第ä¸ĥ
    0.76
    第åħŃ
    0.75
     fourth
    0.73
    第ä¹Ŀ
    0.72
    第åħ«
    0.72
    第ä¸ī
    0.71
    Activations Density 0.009%

    No Known Activations