© 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. 41742
    Prev
    Next
    INDEX
    Explanations

    code

    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
    æĹł
    -1.51
    çĦ¡
    -1.34
     void
    -1.05
    æĹłäºº
    -1.05
    void
    -0.98
    	void
    -0.92
    æĹłæīĢ
    -0.91
     Void
    -0.86
    Void
    -0.84
     VOID
    -0.84
    POSITIVE LOGITS
    ioned
    0.27
     kidnapped
    0.24
    eward
    0.23
    xAA
    0.23
     Accent
    0.22
    adier
    0.22
    çĪ±ç¾İ
    0.21
    tal
    0.21
    indent
    0.21
    itor
    0.21
    Activations Density 0.011%

    No Known Activations