© 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. 130434
    Prev
    Next
    INDEX
    Explanations

    documents, code

    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
    ivi
    -0.31
    è¹ij
    -0.30
     foss
    -0.26
    atts
    -0.26
    ä»»ä½ķ人éĥ½
    -0.25
    æīĢèĥ½
    -0.24
    oul
    -0.24
     feet
    -0.24
    éļ¶
    -0.24
    å²³
    -0.24
    POSITIVE LOGITS
    -Identifier
    0.30
    ULSE
    0.25
     Harding
    0.25
    à¹ĥà¸Ī
    0.24
    æĬ¤èº«
    0.24
    Ấ
    0.24
    berra
    0.24
    EventData
    0.23
    éĻ¤
    0.23
     migrationBuilder
    0.23
    Activations Density 0.027%

    No Known Activations