© 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. 22-TRANSCODER-HP
    7. 97934
    Prev
    Next
    INDEX
    Explanations

    tend

    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
    teen
    -0.28
    rena
    -0.27
    	↵	↵	↵
    -0.26
    notated
    -0.26
    thermal
    -0.26
    éĻ¢
    -0.25
    åı¯çĶ¨
    -0.25
    åı¯éĢļè¿ĩ
    -0.25
    åĽ¾ä¸º
    -0.24
    dest
    -0.24
    POSITIVE LOGITS
    ulum
    0.28
    fel
    0.28
    erness
    0.28
    paper
    0.25
    orial
    0.24
    osite
    0.24
    edly
    0.24
    té
    0.23
    зи
    0.23
    ings
    0.23
    Activations Density 0.023%

    No Known Activations