© 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. 24889
    Prev
    Next
    INDEX
    Explanations

    Various nouns

    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
     sinks
    -0.28
    èħĶ
    -0.27
    jing
    -0.26
    åĪį
    -0.26
    UBLIC
    -0.26
    posable
    -0.25
    feb
    -0.25
    _constructor
    -0.24
    -Jul
    -0.24
    å¯ĨåĪĩ
    -0.24
    POSITIVE LOGITS
    天çĶŁ
    0.25
    izer
    0.25
     Wolfe
    0.24
    _bold
    0.24
    textarea
    0.24
    èı²å°Ķ
    0.24
     Fight
    0.23
     territory
    0.23
    astr
    0.23
    Works
    0.23
    Activations Density 0.051%

    No Known Activations