© 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. 42056
    Prev
    Next
    INDEX
    Explanations

    emoticons

    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
    ]]:↵
    -0.62
    "):↵
    -0.62
    '):↵
    -0.59
    ])):↵
    -0.59
    ')):↵
    -0.59
    ']:↵
    -0.57
    ]):↵
    -0.57
    '):č↵
    -0.55
    "]:↵
    -0.55
    "):č↵
    -0.55
    POSITIVE LOGITS
    ï¼ļ
    0.67
    âĪ¶
    0.57
    :L
    0.57
    :-
    0.57
     :
    0.56
     ï¼ļ
    0.56
    +:
    0.55
    :**
    0.55
    :S
    0.55
    :y
    0.54
    Activations Density 0.009%

    No Known Activations