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

    Neuronpedia

    APICircuit 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. 31263
    Prev
    Next
    INDEX
    Explanations

    Components of systems

    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
     mane
    -0.07
     Coroutine
    -0.07
    acd
    -0.07
    ']))
    ↵
    -0.07
     le
    -0.07
    adder
    -0.07
     gon
    -0.07
    鹭
    -0.06
     carne
    -0.06
     nihil
    -0.06
    POSITIVE LOGITS
     External
    0.07
    사를
    0.07
    ('',
    0.07
    //----------------------------------------------------------------------------
    0.07
    (region
    0.07
    部委
    0.07
    _Session
    0.07
    ンド
    0.07
    Esc
    0.07
    	Base
    0.07
    Activations Density 0.258%

    No Known Activations