© 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. 150346
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    llen
    -0.29
     Dud
    -0.28
     unified
    -0.27
     Holds
    -0.26
     glGen
    -0.26
    ition
    -0.25
     balk
    -0.25
    temp
    -0.24
    _sid
    -0.24
     unify
    -0.24
    POSITIVE LOGITS
    çī¹
    0.29
    WARDS
    0.26
    ñas
    0.26
    emies
    0.25
    atsu
    0.25
    ety
    0.25
    ade
    0.25
    åĨľæ°ijå·¥
    0.24
    å®Įåħ¨
    0.24
    pts
    0.24
    Activations Density 0.040%

    No Known Activations