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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 2729
    Prev
    Next
    INDEX
    Explanations

    math/scientific contexts

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曼联
    -0.08
    hunter
    -0.07
    扊
    -0.07
    ことができる
    -0.07
    -fw
    -0.07
     ham
    -0.07
    _gt
    -0.06
     tougher
    -0.06
     without
    -0.06
     through
    -0.06
    POSITIVE LOGITS
    ARING
    0.07
    有趣
    0.07
    olor
    0.07
     printing
    0.07
    蓝色
    0.07
     Stereo
    0.07
     PREF
    0.07
     rivalry
    0.07
    ()):
    0.07
     abusive
    0.07
    Activations Density 0.157%

    No Known Activations