© 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. 150273
    Prev
    Next
    INDEX
    Explanations

    used

    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
    western
    -0.27
    verbs
    -0.25
     legis
    -0.25
    ngen
    -0.25
    plusplus
    -0.25
    ä¸Ĭå¹´
    -0.24
    INGS
    -0.24
    )Math
    -0.24
    ä½ľåĵģåĨħ容
    -0.24
    DeviceInfo
    -0.23
    POSITIVE LOGITS
    ascar
    0.33
    åı¯çĶ¨äºİ
    0.28
    èĮĥçķ´
    0.27
    çŃīè¡Įä¸ļ
    0.27
    åIJĦç§į
    0.27
    :;↵
    0.27
     various
    0.26
    å¹¿æ³ĽåºĶçĶ¨
    0.26
     Einsatz
    0.26
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.26
    Activations Density 0.208%

    No Known Activations