Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25273
    Prev
    Next
    INDEX
    Explanations

    Alibaba

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⌟
    -0.08
     Vie
    -0.07
    嫚
    -0.07
     hurdles
    -0.07
     guise
    -0.07
     Julio
    -0.07
    ateg
    -0.07
    素材
    -0.07
     Imp
    -0.07
    ሥ
    -0.07
    POSITIVE LOGITS
    协商
    0.07
    圓
    0.07
    (labels
    0.07
    learn
    0.06
     adher
    0.06
    犯罪
    0.06
    .CharField
    0.06
    -making
    0.06
    kal
    0.06
    Conditional
    0.06
    Activations Density 0.017%

    No Known Activations