© 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. 24-TRANSCODER-HP
    7. 149771
    Prev
    Next
    INDEX
    Explanations

    settlement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohl
    -0.26
    å¸ĺ
    -0.26
     Kurd
    -0.25
    ç±¼
    -0.25
    åĩłå®¶
    -0.25
    maze
    -0.24
    ermann
    -0.24
    tran
    -0.24
    éĶ®çĽĺ
    -0.24
     assort
    -0.23
    POSITIVE LOGITS
    er
    0.32
    es
    0.30
    est
    0.29
    its
    0.28
    移åĬ¨
    0.28
    der
    0.26
    ients
    0.26
    i
    0.26
     move
    0.25
    æŁ¢
    0.25
    Activations Density 0.466%

    No Known Activations