© 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. 57190
    Prev
    Next
    INDEX
    Explanations

    Kirst

    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
    说æĺ¯
    -0.29
    ãģŀ
    -0.25
     bien
    -0.24
    éĻĭ
    -0.24
    .hidden
    -0.24
    well
    -0.24
     stiff
    -0.23
     Dien
    -0.23
    è¶³å¤ŁçļĦ
    -0.23
    ãģ¨æĢĿãģ£ãģ¦ãģĦãĤĭ
    -0.23
    POSITIVE LOGITS
    宸
    0.29
    kre
    0.28
    learn
    0.26
    еÑĢи
    0.25
    æĬ½
    0.25
     enumerator
    0.25
    å°Ĭ
    0.25
    eid
    0.25
    á»ħn
    0.24
    ç¦ıå¾·
    0.24
    Activations Density 0.184%

    No Known Activations