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. 71619
    Prev
    Next
    INDEX
    Explanations

    Software/hardware updates

    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
     nuôi
    -0.07
     공동
    -0.07
    入学
    -0.07
     наход
    -0.07
    Language
    -0.07
    驻村
    -0.07
    	strcat
    -0.07
    hasMany
    -0.07
     Rose
    -0.07
    伸び
    -0.07
    POSITIVE LOGITS
    ście
    0.08
     mnemonic
    0.07
     bre
    0.07
    Execute
    0.07
    .details
    0.07
    Cal
    0.07
    ฤ
    0.07
    ⏎
    0.07
     añ
    0.07
    atalog
    0.07
    Activations Density 0.512%

    No Known Activations