© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 868
    Prev
    Next
    INDEX
    Explanations

    blockchain technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (wp
    -0.07
     systemic
    -0.07
    (weather
    -0.07
    _AES
    -0.07
    רתי
    -0.07
     Ellen
    -0.07
    헉
    -0.07
    躇
    -0.07
    -it
    -0.06
    -section
    -0.06
    POSITIVE LOGITS
     Sum
    0.07
    >());↵↵
    0.07
     vows
    0.07
    <|endoftext|>
    0.07
    _rhs
    0.07
     cùng
    0.07
    urchases
    0.07
    忌
    0.06
     Cruise
    0.06
     Any
    0.06
    Activations Density 0.065%

    No Known Activations