© 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. 41364
    Prev
    Next
    INDEX
    Explanations

    Determine

    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
    å°ĨæĪIJ为
    -0.28
    acific
    -0.27
    è¿Ļæĺ¯æĪij们
    -0.27
    RIX
    -0.26
    è¶ħè¿ĩäºĨ
    -0.26
     becoming
    -0.26
     Become
    -0.26
    Become
    -0.25
     Declarations
    -0.24
    丼æŀĹ
    -0.24
    POSITIVE LOGITS
    :
    0.33
    bler
    0.32
    :↵↵
    0.31
    :↵
    0.30
    :-
    0.27
    -upper
    0.27
     dy
    0.26
     S
    0.26
     whole
    0.26
    :**
    0.26
    Activations Density 0.028%

    No Known Activations