© 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. 149708
    Prev
    Next
    INDEX
    Explanations

    with

    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
    å¼ĢéŨ
    -0.27
    çģµæĦŁ
    -0.26
    èħ°
    -0.26
     jobs
    -0.25
    æĸ°çīĪ
    -0.25
    æ£Ģ
    -0.24
     nut
    -0.24
    nan
    -0.24
    ynet
    -0.24
    unan
    -0.23
    POSITIVE LOGITS
    è£
    0.29
     shielding
    0.28
    power
    0.28
    edis
    0.28
    æĬĹæĭĴ
    0.27
    essler
    0.26
    ivamente
    0.25
    fulness
    0.25
    etas
    0.24
     szczegóÅĤowo
    0.24
    Activations Density 0.118%

    No Known Activations