© 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. 23-TRANSCODER-HP
    7. 24815
    Prev
    Next
    INDEX
    Explanations

    fill-in-the-blank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getSupportActionBar
    -0.28
    èij³
    -0.26
    :init
    -0.25
     track
    -0.25
    unkt
    -0.24
    fare
    -0.24
     ÅŁu
    -0.24
    æĿľåħ°
    -0.24
    å¯ĴåĨ¬
    -0.24
    估计
    -0.23
    POSITIVE LOGITS
    pl
    0.28
    ÑĢаз
    0.28
    æĦĪ
    0.25
    æĿ¥ä¸įåıĬ
    0.25
    .au
    0.24
    大æī¹
    0.24
    ï¸ı
    0.24
    PL
    0.23
    div
    0.23
    .opend
    0.23
    Activations Density 0.025%

    No Known Activations