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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    6. 85104
    Prev
    Next
    INDEX
    Explanations

    authors and their works

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blasph
    -0.07
    乡土
    -0.06
    umen
    -0.06
    𬭳
    -0.06
     KeyboardInterrupt
    -0.06
    dont
    -0.06
     trustworthy
    -0.06
    مؤشر
    -0.06
     Knight
    -0.06
    يار
    -0.06
    POSITIVE LOGITS
    ---</
    0.08
    _PROGRAM
    0.07
    -active
    0.07
    -solid
    0.07
     PREFIX
    0.07
     props
    0.07
    ulse
    0.07
     converts
    0.07
    编
    0.07
    (balance
    0.07
    Activations Density 0.075%

    No Known Activations