© 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. 149986
    Prev
    Next
    INDEX
    Explanations

    (

    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
     strings
    -0.26
    åij¨è¾¹
    -0.25
    strings
    -0.25
    裳
    -0.24
    oram
    -0.24
    è§ĦåĪĻ
    -0.24
    éĿĻçĶµ
    -0.24
     dashes
    -0.24
    æļĹ
    -0.23
    è¯ģæĺİ
    -0.23
    POSITIVE LOGITS
     FOX
    0.30
    chos
    0.26
    _$_
    0.26
    sphere
    0.25
    enco
    0.25
     Nationwide
    0.25
    culos
    0.25
     affiliation
    0.24
    %x
    0.24
    ãģĭãĤĮ
    0.23
    Activations Density 0.220%

    No Known Activations