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. 36050
    Prev
    Next
    INDEX
    Explanations

    exhibition

    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
    蟒
    -0.07
    也没
    -0.07
     Ngọc
    -0.07
    ɮ
    -0.07
     mpz
    -0.07
     Dave
    -0.06
     Mvc
    -0.06
     dns
    -0.06
     Gdk
    -0.06
    (parser
    -0.06
    POSITIVE LOGITS
     cohesion
    0.07
     disponible
    0.07
    ulta
    0.07
    肩膀
    0.07
    脱颖而出
    0.07
     alleen
    0.06
     quarantine
    0.06
    (cor
    0.06
    .How
    0.06
    风尚
    0.06
    Activations Density 0.010%

    No Known Activations