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. 7061
    Prev
    Next
    INDEX
    Explanations

    Parenthesis/dash

    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
    _course
    -0.08
     Bunifu
    -0.08
    胡萝卜
    -0.08
    FillColor
    -0.07
    גנטי
    -0.07
     Sword
    -0.07
    _sched
    -0.07
    width
    -0.06
     colum
    -0.06
     Pé
    -0.06
    POSITIVE LOGITS
     chr
    0.07
     significantly
    0.07
    	SC
    0.07
    :'',↵
    0.07
     unb
    0.06
    	pr
    0.06
     hb
    0.06
     ageing
    0.06
     oi
    0.06
    渣
    0.06
    Activations Density 0.036%

    No Known Activations