© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151145
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    igr
    -0.28
     paired
    -0.26
    åĬ©æĶ»
    -0.25
    æ¼Ĥæµģ
    -0.25
     footing
    -0.24
    çĸ¯çĭĤ
    -0.24
    rush
    -0.24
    éªijè¡Į
    -0.24
     riding
    -0.24
     momentum
    -0.24
    POSITIVE LOGITS
    adesh
    0.30
    ĵį
    0.27
    -navbar
    0.25
    æĥħåĨµ
    0.25
    ä¸İæŶ
    0.25
    ört
    0.24
     OrderedDict
    0.24
    æŃĩ
    0.24
    çݰ象
    0.24
    å¹³éĿ¢
    0.23
    Activations Density 0.005%

    No Known Activations