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. 7186
    Prev
    Next
    INDEX
    Explanations

    chemical symbols

    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
     unreal
    -0.10
    创新发展
    -0.08
     varying
    -0.07
    실
    -0.07
     kapsamında
    -0.07
    欤
    -0.07
    annes
    -0.06
    ethical
    -0.06
    getti
    -0.06
    ucursal
    -0.06
    POSITIVE LOGITS
    �
    0.07
    -ST
    0.07
    "`
    0.06
    LB
    0.06
    是一個
    0.06
    _small
    0.06
    ,SIGNAL
    0.06
     заб
    0.06
     !"
    0.06
    -la
    0.06
    Activations Density 0.007%

    No Known Activations