© 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. 129402
    Prev
    Next
    INDEX
    Explanations

    math/logic/programming

    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
    è§Ħå®ļ
    -0.26
     two
    -0.25
     *(*
    -0.25
     Areas
    -0.25
    çİ°çĬ¶
    -0.24
    åħ¼å®¹
    -0.24
    æĭŁ
    -0.24
    ercul
    -0.23
     __(
    -0.23
    äºĮç»´
    -0.23
    POSITIVE LOGITS
    æĪij以为
    0.28
    ç¯Ģ
    0.27
    UGE
    0.26
    以çĤº
    0.26
    úb
    0.26
     DSL
    0.26
    URA
    0.25
    atively
    0.25
    nesia
    0.25
     eskort
    0.25
    Activations Density 0.008%

    No Known Activations