© 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. 97656
    Prev
    Next
    INDEX
    Explanations

    kingdom

    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
    cession
    -0.25
    anco
    -0.25
    åŀĭä¼ģä¸ļ
    -0.24
    olatile
    -0.23
    errals
    -0.22
    (expression
    -0.22
    iston
    -0.22
    å°ķ
    -0.22
    =search
    -0.22
    çĮľ
    -0.22
    POSITIVE LOGITS
    -ending
    0.30
    -wide
    0.29
     hall
    0.26
    chaft
    0.26
    oise
    0.25
     rep
    0.25
    zyst
    0.25
    -long
    0.24
    wide
    0.24
    ohl
    0.24
    Activations Density 0.104%

    No Known Activations