© 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. 98236
    Prev
    Next
    INDEX
    Explanations

    Subwords

    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
     chat
    -0.27
    VEC
    -0.25
    Chat
    -0.24
    ãģĸ
    -0.24
    çĹĺ
    -0.23
    ноÑģÑĤ
    -0.23
     bounced
    -0.23
     fasc
    -0.23
    ppers
    -0.23
    inus
    -0.22
    POSITIVE LOGITS
    /wiki
    0.25
    eral
    0.25
    ario
    0.25
    å®Į
    0.24
    storybook
    0.24
    åĪł
    0.23
    ordinal
    0.23
    actoring
    0.23
    导æ¼Ķ
    0.22
    á»ĵ
    0.22
    Activations Density 0.009%

    No Known Activations