© 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. 32-TRANSCODER-HP
    7. 43091
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partner
    -1.22
     partners
    -1.13
     Partner
    -1.08
    partner
    -0.99
     Partners
    -0.98
    Partner
    -0.97
     partnerships
    -0.89
     partnered
    -0.88
     partnership
    -0.87
    partners
    -0.85
    POSITIVE LOGITS
    apk
    0.27
    ulpt
    0.26
    theses
    0.25
    alers
    0.25
    æķ£åıij
    0.25
     Pure
    0.24
     gönder
    0.24
     pure
    0.24
    lotte
    0.24
    ượng
    0.24
    Activations Density 0.002%

    No Known Activations