© 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. 88297
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    åıĹ访
    -0.27
    uning
    -0.26
    unte
    -0.25
    åŀĭ
    -0.25
    inalg
    -0.25
    ve
    -0.25
    uxe
    -0.24
    odem
    -0.24
     Borg
    -0.23
    åĽŀå½Ĵ
    -0.23
    POSITIVE LOGITS
    åĮħæĭ¬
    0.39
     includes
    0.38
     include
    0.38
     notamment
    0.37
    æ¯Ķå¦Ĥ
    0.36
     includ
    0.36
     notably
    0.35
    ä¾ĭå¦Ĥ
    0.35
     including
    0.34
     namely
    0.33
    Activations Density 0.001%

    No Known Activations