© 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. 88334
    Prev
    Next
    INDEX
    Explanations

    water

    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
    aly
    -0.28
    éĤ£éĩĮ
    -0.24
    ei
    -0.24
    éĢĴ
    -0.24
    Immutable
    -0.24
    elem
    -0.24
    ual
    -0.23
    iÄį
    -0.23
    nor
    -0.23
    jun
    -0.23
    POSITIVE LOGITS
     appeal
    0.26
    signals
    0.26
    wares
    0.26
    å¸ĪèĮĥ大åѦ
    0.25
    amel
    0.25
    gerald
    0.24
    è¶ĭ
    0.24
     appeals
    0.24
    .blit
    0.23
     ado
    0.23
    Activations Density 0.076%

    No Known Activations