© 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. 57166
    Prev
    Next
    INDEX
    Explanations

    Date/date

    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
    è°Ħ
    -0.24
    åݻ年åIJĮæľŁ
    -0.23
    xca
    -0.23
    åħ¬åı¸çļĦ
    -0.23
    顺åĬ¿
    -0.23
    _creator
    -0.23
    æłĩé¢ĺ
    -0.23
    ä½ľèĢħæľ¬äºº
    -0.22
    åŁºäºİ
    -0.22
     backwards
    -0.22
    POSITIVE LOGITS
    æī§æķĻ
    0.30
    (s
    0.27
    picker
    0.27
    æīĵäºĨ
    0.27
    æİ
    0.26
    槿
    0.26
     stocking
    0.25
    á»ķi
    0.25
    ccoli
    0.25
    .dispose
    0.25
    Activations Density 0.025%

    No Known Activations