© 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. 150634
    Prev
    Next
    INDEX
    Explanations

    technical document excerpts

    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
    داÙĨ
    -0.29
    ศาส
    -0.27
    bies
    -0.26
     shadow
    -0.26
    sec
    -0.26
    SEC
    -0.26
    illon
    -0.25
     ref
    -0.25
    Sec
    -0.25
     reward
    -0.25
    POSITIVE LOGITS
    throp
    0.28
    rac
    0.28
    RIPT
    0.28
     travellers
    0.27
    plevel
    0.27
    rip
    0.27
    bsite
    0.26
    rapper
    0.26
    isable
    0.25
     Races
    0.25
    Activations Density 0.007%

    No Known Activations