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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 84717
    Prev
    Next
    INDEX
    Explanations

    language generation

    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
    ố
    -0.07
    Canonical
    -0.07
    _dev
    -0.07
    _cert
    -0.07
     nominated
    -0.07
     Dodge
    -0.07
     требования
    -0.07
     referee
    -0.07
    颁发
    -0.07
     rendre
    -0.06
    POSITIVE LOGITS
     Psalm
    0.07
    ־
    0.07
    现已
    0.07
    DEFAULT
    0.06
     makeStyles
    0.06
    风控
    0.06
    Ꭰ
    0.06
    ‘
    0.06
    将于
    0.06
     SCI
    0.06
    Activations Density 0.040%

    No Known Activations