© 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. 150222
    Prev
    Next
    INDEX
    Explanations

    least

    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
     than
    -0.38
    Than
    -0.35
    ensa
    -0.33
    _THAN
    -0.33
    -than
    -0.31
    than
    -0.31
     THAN
    -0.31
     Than
    -0.30
     gou
    -0.28
    _than
    -0.27
    POSITIVE LOGITS
    ä¹ĭåŁİ
    0.27
    以为
    0.27
    interpreted
    0.26
    eurs
    0.26
     interpreted
    0.25
    竺
    0.24
    é«ĺåľ°
    0.24
    æĮł
    0.24
    -known
    0.24
    Fast
    0.24
    Activations Density 0.370%

    No Known Activations