© 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. 24-TRANSCODER-HP
    7. 150066
    Prev
    Next
    INDEX
    Explanations

    Change or progression

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .TabIndex
    -0.25
     HomeController
    -0.24
    gradation
    -0.24
    ahlen
    -0.24
    ÙĨØ©
    -0.23
     Ending
    -0.23
    ç²īæľ«
    -0.23
    .native
    -0.23
     loc
    -0.23
    Gl
    -0.22
    POSITIVE LOGITS
    bü
    0.28
    strup
    0.24
    åįĥæĸ¹çĻ¾
    0.24
    ä½łçļĦ
    0.24
     kijken
    0.23
     charities
    0.23
    æĪij们çļĦ
    0.23
    ог
    0.23
    :update
    0.23
    ëĭ¤ê°Ģ
    0.23
    Activations Density 1.182%

    No Known Activations