© 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. 32-TRANSCODER-HP
    7. 41230
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    and
    -0.32
    ayout
    -0.27
     effects
    -0.26
    ↵↵
    -0.26
    on
    -0.25
    ↵
    -0.25
     hardware
    -0.25
    è¶Ĭ好
    -0.25
    "
    -0.25
    -and
    -0.25
    POSITIVE LOGITS
    æİĴæ¯Ĵ
    0.30
    å¸ļ
    0.27
    å®īåħ¨äºĭæķħ
    0.26
    è¾Ľè¾£
    0.26
    èĭĭ
    0.25
    ysqli
    0.25
    ç½ij讯
    0.25
     *(*
    0.24
     )[
    0.24
     CrossAxisAlignment
    0.24
    Activations Density 0.065%

    No Known Activations