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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 26180
    Prev
    Next
    INDEX
    Explanations

    _LONG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    槃
    -0.08
    贲
    -0.07
    ביטול
    -0.07
    (height
    -0.07
    /m
    -0.07
    	j
    -0.07
     Mansion
    -0.07
    埘
    -0.07
    -open
    -0.07
    .nlm
    -0.07
    POSITIVE LOGITS
    ключи
    0.07
    了解一下
    0.07
    yor
    0.07
     snakes
    0.07
    ensem
    0.07
    مسؤول
    0.07
     unethical
    0.07
    ihat
    0.06
     lemon
    0.06
     enchanted
    0.06
    Activations Density 0.000%

    No Known Activations