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. 115212
    Prev
    Next
    INDEX
    Explanations

    code snippets involving files

    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
    中新网
    -0.07
    Read
    -0.07
     spat
    -0.07
    (range
    -0.06
     查询
    -0.06
    里
    -0.06
     vídeos
    -0.06
    .randint
    -0.06
    border
    -0.06
    	Map
    -0.06
    POSITIVE LOGITS
     completely
    0.07
    -solid
    0.07
    Marsh
    0.07
     overcrow
    0.07
     cooling
    0.07
    _No
    0.07
    _JOIN
    0.07
     abundance
    0.07
     balances
    0.07
    ObjectId
    0.07
    Activations Density 0.011%

    No Known Activations