© 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. 150202
    Prev
    Next
    INDEX
    Explanations

    Technical Q\&A

    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
    便
    -0.27
    igne
    -0.27
    ç»Ń
    -0.26
    inus
    -0.26
    anking
    -0.25
    ÑģпоÑĢ
    -0.24
    ä¸ĩ个
    -0.24
    ä¸ĸ
    -0.24
    hooks
    -0.24
    anya
    -0.24
    POSITIVE LOGITS
     treats
    0.30
     deals
    0.29
     appeared
    0.28
     penal
    0.27
     treat
    0.27
     smelled
    0.26
     thr
    0.26
     dealt
    0.26
     wer
    0.25
     wouldn
    0.25
    Activations Density 0.153%

    No Known Activations