© 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. 129488
    Prev
    Next
    INDEX
    Explanations

    9

    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
    eve
    -0.30
    æī§
    -0.28
    iator
    -0.28
    rier
    -0.27
    artz
    -0.27
    ÅĽcie
    -0.27
    åŁ·
    -0.27
    zs
    -0.27
    çĻ»éĮĦ
    -0.26
    razier
    -0.26
    POSITIVE LOGITS
    诸å¦Ĥ
    0.40
    èѬå¦Ĥ
    0.36
    æ¯Ķå¦Ĥ
    0.36
    ä¾ĭå¦Ĥ
    0.36
     including
    0.32
    åĮħæĭ¬
    0.31
    æ¯Ķå¦Ĥ说
    0.30
    å¦Ĥ
    0.28
     like
    0.27
    éĨĴ
    0.27
    Activations Density 0.014%

    No Known Activations