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. 36256
    Prev
    Next
    INDEX
    Explanations

    punctuation after "al"

    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
    ems
    -0.09
    提炼
    -0.07
    feit
    -0.07
    voie
    -0.07
     deceit
    -0.07
    increments
    -0.07
    طم
    -0.07
     neur
    -0.07
    uesday
    -0.07
    	File
    -0.07
    POSITIVE LOGITS
     normalized
    0.07
    _table
    0.07
     LEVEL
    0.07
     productList
    0.07
    댕
    0.07
    |$
    0.07
    _STORE
    0.07
     женщин
    0.07
    的影响
    0.07
    的重要性
    0.06
    Activations Density 0.006%

    No Known Activations