© 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. 150208
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     Cornell
    -0.29
    TARGET
    -0.29
     Columbia
    -0.27
    addle
    -0.25
    olumbia
    -0.24
     unrecognized
    -0.24
     Princeton
    -0.23
    头èĦij
    -0.23
     specialty
    -0.23
    ertype
    -0.23
    POSITIVE LOGITS
     organisation
    0.32
     aluminium
    0.31
    omet
    0.30
    chemas
    0.30
     Aluminium
    0.30
    Whilst
    0.29
     Whilst
    0.28
     organisations
    0.28
    isations
    0.27
     Labour
    0.27
    Activations Density 0.907%

    No Known Activations