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. 109901
    Prev
    Next
    INDEX
    Explanations

    informative

    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
     mailed
    -0.07
     una
    -0.07
    (ix
    -0.07
     cardio
    -0.07
     suits
    -0.07
    (done
    -0.06
    暑
    -0.06
    (curr
    -0.06
    商量
    -0.06
    镁
    -0.06
    POSITIVE LOGITS
    ctype
    0.07
    ize
    0.07
     useForm
    0.07
    indows
    0.07
    -.
    0.07
     educate
    0.07
    oit
    0.07
    _PREVIEW
    0.07
    …”
    0.07
    mination
    0.07
    Activations Density 0.015%

    No Known Activations