© 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. 130152
    Prev
    Next
    INDEX
    Explanations

    Needs/requirements

    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
    jes
    -0.26
    ow
    -0.25
    ince
    -0.25
    çĨŁ
    -0.25
    æŃ£
    -0.24
    BOOL
    -0.24
    lik
    -0.24
    OW
    -0.24
     justify
    -0.24
    lio
    -0.24
    POSITIVE LOGITS
     mysterious
    0.27
     mysteries
    0.27
     myster
    0.26
    .Board
    0.26
     nothing
    0.25
    (eq
    0.25
    该éĻ¢
    0.25
    Suggestions
    0.25
    ]";↵
    0.25
    aque
    0.24
    Activations Density 0.014%

    No Known Activations