© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 86922
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exon
    -0.06
    可靠的
    -0.06
    ベスト
    -0.06
    もち
    -0.06
    ובל
    -0.06
    콥
    -0.06
     inhibited
    -0.06
    那
    -0.06
    аб
    -0.06
    isin
    -0.06
    POSITIVE LOGITS
    _USERS
    0.07
    _Run
    0.07
    /game
    0.07
    ("%.
    0.07
    גוף
    0.07
    erral
    0.06
    -os
    0.06
    ﹿ
    0.06
    avs
    0.06
    :n
    0.06
    Activations Density 0.038%

    No Known Activations