© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 88196
    Prev
    Next
    INDEX
    Explanations

    Previous and next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ~-
    -0.28
    åīįåIJİ
    -0.27
    iscrim
    -0.25
    ORA
    -0.25
    ä¸ĩ个
    -0.25
    ayed
    -0.24
    makt
    -0.24
    éŃĶæľ¯
    -0.23
    LA
    -0.23
    å½ĵæĹ¶
    -0.23
    POSITIVE LOGITS
    dig
    0.26
    ick
    0.25
     Flat
    0.25
    icum
    0.25
    ventions
    0.24
     ire
    0.23
     Que
    0.23
    估计
    0.23
     envision
    0.23
    opot
    0.23
    Activations Density 0.011%

    No Known Activations