© 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. 23-TRANSCODER-HP
    7. 24169
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahoo
    -0.26
    ä¸ŃåĽ½çī¹èī²
    -0.25
    ockets
    -0.25
    è°ģçŁ¥
    -0.25
    ä½Ĩä»į
    -0.25
    æ²»çĸĹæĸ¹æ³ķ
    -0.24
    ivr
    -0.24
    æĥ³åĪ°äºĨ
    -0.24
    herent
    -0.24
     ê·¸ëŁ¼
    -0.24
    POSITIVE LOGITS
    åī¯
    0.28
    hom
    0.28
     unsus
    0.26
     succeeding
    0.26
    ÅĽÄĩ
    0.25
    èĥ¶åĽĬ
    0.25
    ColumnType
    0.25
    imson
    0.24
     intox
    0.24
    à¤ī
    0.24
    Activations Density 0.003%

    No Known Activations