© 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. 31-TRANSCODER-HP
    7. 19068
    Prev
    Next
    INDEX
    Explanations

    mort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansi
    -0.26
    aco
    -0.25
    colo
    -0.25
     sip
    -0.25
    èij±
    -0.25
    inky
    -0.25
    æ´½
    -0.25
     throat
    -0.24
    che
    -0.24
    车åİ¢
    -0.24
    POSITIVE LOGITS
    er
    0.26
    ä¹ŁæĹłæ³ķ
    0.26
    omial
    0.25
    æŶæĬ¥
    0.25
     Morr
    0.24
    MF
    0.23
    æ¸Ľ
    0.23
    shr
    0.23
    失æķĪ
    0.23
    èĬį
    0.23
    Activations Density 0.099%

    No Known Activations