© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162395
    Prev
    Next
    INDEX
    Explanations

    Paths, containers, small objects

    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
     TM
    -0.29
    HK
    -0.27
    èķĥ
    -0.27
    TU
    -0.27
    TM
    -0.26
    åĴĮåħ¶ä»ĸ
    -0.26
     Erg
    -0.25
    inka
    -0.25
    his
    -0.24
    []
    -0.24
    POSITIVE LOGITS
    quier
    0.27
    enburg
    0.26
    ={({
    0.25
    MARY
    0.25
    æĥ©æĪĴ
    0.24
    ffective
    0.24
    çŀĢ
    0.24
    shapes
    0.24
    æݨèįIJ
    0.24
    "];↵
    0.23
    Activations Density 0.009%

    No Known Activations