© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 84831
    Prev
    Next
    INDEX
    Explanations

    job postings

    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
     lp
    -0.07
     sg
    -0.07
    paque
    -0.07
    scaled
    -0.07
    paper
    -0.06
    rpc
    -0.06
    novation
    -0.06
    abc
    -0.06
     incorporate
    -0.06
    sale
    -0.06
    POSITIVE LOGITS
    檗
    0.07
    �
    0.07
     erot
    0.07
    눠
    0.07
    _IList
    0.07
    عظيم
    0.07
     índ
    0.06
    (exception
    0.06
     Yaz
    0.06
    -icons
    0.06
    Activations Density 0.031%

    No Known Activations