© 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. 43071
    Prev
    Next
    INDEX
    Explanations

    't

    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
     reflect
    -0.36
     direct
    -0.35
     ever
    -0.34
     Reflect
    -0.33
    reflect
    -0.33
    -ever
    -0.32
    ever
    -0.32
    Reflect
    -0.31
    direct
    -0.29
    ä¹Łä¸įè¦ģ
    -0.27
    POSITIVE LOGITS
     yet
    0.29
    åį´
    0.26
    ailles
    0.25
     study
    0.25
    agements
    0.25
    зв
    0.25
    çŁ³å®¶
    0.25
    growth
    0.25
    åİī
    0.25
    ccoli
    0.25
    Activations Density 0.016%

    No Known Activations