© 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. 87767
    Prev
    Next
    INDEX
    Explanations

    Numbers and citations

    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
    涯
    -0.27
    çļĦèģĮä¸ļ
    -0.27
    çĭ¬
    -0.27
    ABCDE
    -0.27
    å®Īä½ı
    -0.27
    tid
    -0.26
    æĸĩæ¡£
    -0.25
    ç©¿è¡£
    -0.25
     bathroom
    -0.25
    éĵ¶è¡Įä¸ļ
    -0.24
    POSITIVE LOGITS
    оÑī
    0.35
    ÑĤоÑĢ
    0.29
     locally
    0.29
    çºł
    0.28
    anon
    0.27
     rep
    0.26
     local
    0.26
    nant
    0.25
    kie
    0.24
     integr
    0.24
    Activations Density 0.029%

    No Known Activations