© 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. 149842
    Prev
    Next
    INDEX
    Explanations

    rising in rank

    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
    éªĮ
    -0.27
    +t
    -0.25
    Set
    -0.25
    vised
    -0.24
    acie
    -0.24
    éĹ®æĪij
    -0.24
    ahi
    -0.24
    mm
    -0.24
    ERVE
    -0.24
     pH
    -0.24
    POSITIVE LOGITS
    rimon
    0.29
    ·»
    0.29
    ìķ
    0.28
    _placement
    0.26
     cum
    0.26
    æijĩ
    0.26
    cum
    0.26
    ANEL
    0.26
    AttributeName
    0.26
     intellectual
    0.25
    Activations Density 0.023%

    No Known Activations