© 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. 23-TRANSCODER-HP
    7. 25195
    Prev
    Next
    INDEX
    Explanations

    arn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽłä¸ºæĪij
    -0.27
    arity
    -0.26
    bef
    -0.25
    å¦Ĥæŀľæĺ¯
    -0.25
    ëĵľ
    -0.24
    åį³ä½¿æĺ¯
    -0.24
    åĪĨéĴŁ
    -0.23
    äºĭæĥħ
    -0.23
    liness
    -0.23
    mina
    -0.23
    POSITIVE LOGITS
    s
    0.29
     Minor
    0.26
    éĵ
    0.24
     Hath
    0.24
    ycling
    0.24
     minor
    0.24
    icate
    0.23
    汪
    0.23
     insol
    0.23
    enticate
    0.23
    Activations Density 0.056%

    No Known Activations