© 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. 129508
    Prev
    Next
    INDEX
    Explanations

    fibr

    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
    .bid
    -0.07
    oogle
    -0.07
    万公里
    -0.07
    時期
    -0.07
    :UIControlStateNormal
    -0.06
     groom
    -0.06
    であろう
    -0.06
     partnerships
    -0.06
    草坪
    -0.06
    udson
    -0.06
    POSITIVE LOGITS
    ,SLOT
    0.08
    ksam
    0.07
    سلط
    0.07
     confronted
    0.07
     EAST
    0.07
    sorted
    0.06
     sensory
    0.06
     DVR
    0.06
     starts
    0.06
    较
    0.06
    Activations Density 0.004%

    No Known Activations