© 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. 150998
    Prev
    Next
    INDEX
    Explanations

    uncommon unicode characters

    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
    èĭ±æł¼åħ°
    -0.30
     ÑĢаÑģÑģ
    -0.29
     Sheffield
    -0.27
     charge
    -0.27
    stown
    -0.26
    :nth
    -0.25
    æijĨåľ¨
    -0.25
    charge
    -0.25
    bulk
    -0.25
     sizing
    -0.25
    POSITIVE LOGITS
    宿
    0.29
     Kov
    0.28
    æĭĵ
    0.28
    åħĢ
    0.26
    èĬĤ
    0.25
     Triangle
    0.25
     commodity
    0.25
    -transitional
    0.25
    zte
    0.25
    åĽ¢åľĨ
    0.25
    Activations Density 0.933%

    No Known Activations