© 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. 41301
    Prev
    Next
    INDEX
    Explanations

    so/too

    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
    agu
    -0.31
    ane
    -0.29
     externally
    -0.28
    aves
    -0.28
    ä¹ī
    -0.26
    æ¯Ľ
    -0.26
    à¤ĺ
    -0.25
     gradu
    -0.25
    ades
    -0.25
    绶
    -0.25
    POSITIVE LOGITS
     far
    0.37
     Far
    0.31
    è¿ľ
    0.30
     fx
    0.28
    far
    0.28
    æ¤Ĵ
    0.28
    éģł
    0.27
    失è°ĥ
    0.27
     FAR
    0.27
    _GF
    0.27
    Activations Density 0.009%

    No Known Activations