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. 16342
    Prev
    Next
    INDEX
    Explanations

    assertions

    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
    than
    -0.08
    民间
    -0.08
    ên
    -0.07
     לנ
    -0.07
    _drv
    -0.07
    /V
    -0.07
    Thu
    -0.07
    /
    -0.07
    /inc
    -0.07
    /B
    -0.06
    POSITIVE LOGITS
     shortcomings
    0.08
    غار
    0.07
     Screening
    0.07
     congreg
    0.07
     irresist
    0.07
    _swap
    0.07
     combating
    0.07
    新模式
    0.07
     permitting
    0.07
    arefa
    0.07
    Activations Density 0.043%

    No Known Activations