© 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. 31-TRANSCODER-HP
    7. 18319
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    顽
    -0.28
    -reply
    -0.28
    epam
    -0.26
    æķ¬çķı
    -0.25
    erate
    -0.24
    AMB
    -0.24
    论
    -0.24
     Kub
    -0.23
     Mell
    -0.23
    éķ¿å¤§
    -0.23
    POSITIVE LOGITS
    cas
    0.28
     singly
    0.27
     Immediate
    0.26
    avra
    0.25
    async
    0.25
     async
    0.25
    bid
    0.25
    cats
    0.24
     ÑģамоÑģÑĤоÑı
    0.24
    ynch
    0.24
    Activations Density 0.934%

    No Known Activations