© 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. 97700
    Prev
    Next
    INDEX
    Explanations

    genre

    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
    adium
    -0.25
    eut
    -0.25
    uitive
    -0.25
    aran
    -0.25
    orus
    -0.24
    erdem
    -0.24
    utorial
    -0.24
    -generated
    -0.24
    YNAM
    -0.23
    orca
    -0.23
    POSITIVE LOGITS
    ocity
    0.28
    }-{
    0.25
    ÃŃst
    0.24
    /pop
    0.24
    ãģĹãģ£
    0.24
    heads
    0.23
     classification
    0.23
    /spec
    0.23
    èīºæľ¯å®¶
    0.23
    chief
    0.23
    Activations Density 0.145%

    No Known Activations