© 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. 45620
    Prev
    Next
    INDEX
    Explanations

    Expressing preferences/conditions

    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
     Exam
    -0.08
    /main
    -0.07
    devices
    -0.07
    umbnail
    -0.06
    _PACKET
    -0.06
    _reads
    -0.06
     ARTICLE
    -0.06
     fined
    -0.06
    	username
    -0.06
    .websocket
    -0.06
    POSITIVE LOGITS
    芮
    0.07
     california
    0.07
    'B
    0.07
     unter
    0.07
     nao
    0.06
     обязан
    0.06
    在此之前
    0.06
    售后
    0.06
    yyvsp
    0.06
    できます
    0.06
    Activations Density 0.076%

    No Known Activations