© 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. 20-TRANSCODER-HP
    7. 107422
    Prev
    Next
    INDEX
    Explanations

    misfortune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pie
    -0.28
    bury
    -0.26
    åı°éĺ¶
    -0.26
     orth
    -0.25
    andbox
    -0.25
     serialize
    -0.24
    isters
    -0.24
    ister
    -0.24
    egis
    -0.24
    иÑĢование
    -0.24
    POSITIVE LOGITS
    ingly
    0.33
    ä¹ĭå¤Ħ
    0.24
    æĹ¢æľī
    0.24
     persisted
    0.24
    /Error
    0.24
    magnitude
    0.24
    OfType
    0.24
    xing
    0.23
     magnitude
    0.23
    åĶ¯æľī
    0.23
    Activations Density 82.245%

    No Known Activations