© 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. 33-TRANSCODER-HP
    7. 53232
    Prev
    Next
    INDEX
    Explanations

    inter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uset
    -0.33
    è¡ħ
    -0.30
    éģĵ
    -0.29
    Do
    -0.28
    ä½ĵ
    -0.27
     Do
    -0.27
    itous
    -0.26
     fou
    -0.25
    ainty
    -0.25
    icity
    -0.25
    POSITIVE LOGITS
     наÑĢ
    0.27
    éĴł
    0.26
    ripe
    0.26
     sacrific
    0.25
     reign
    0.25
    室å¤ĸ
    0.25
    åīĬå¼±
    0.25
    jm
    0.25
    æĿ¡
    0.25
     yuk
    0.25
    Activations Density 0.016%

    No Known Activations