© 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. 150957
    Prev
    Next
    INDEX
    Explanations

    [@ or B

    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
    _TestCase
    -0.25
    leh
    -0.25
    ãģ¡ãģª
    -0.24
    导
    -0.24
    wort
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.23
    cı
    -0.23
    lö
    -0.23
    人çĶŁçļĦ
    -0.23
    assa
    -0.23
    POSITIVE LOGITS
     Hind
    0.29
    ä¸į代表
    0.25
     Opport
    0.25
     obs
    0.24
     baik
    0.24
     jade
    0.24
     intimid
    0.24
     Kn
    0.24
    anye
    0.24
    åĭ¤
    0.24
    Activations Density 0.069%

    No Known Activations