© 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. 32-TRANSCODER-HP
    7. 43617
    Prev
    Next
    INDEX
    Explanations

    money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    return
    -0.39
     return
    -0.38
     returns
    -0.34
     returning
    -0.32
    	return
    -0.32
    returns
    -0.31
     Returns
    -0.31
     RETURN
    -0.30
     returned
    -0.30
    Returns
    -0.30
    POSITIVE LOGITS
    à¹ģมà¸Ļ
    0.27
    azon
    0.26
    DUCT
    0.24
    ryn
    0.24
    DU
    0.23
    çĶŁæĹ¥
    0.23
    FW
    0.23
    ĵį
    0.23
     Mana
    0.23
    ATORY
    0.23
    Activations Density 0.002%

    No Known Activations