© 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. 15-RESID-POST-AA
    6. 89240
    Prev
    Next
    INDEX
    Explanations

    term

    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
     of
    -0.10
    一本书
    -0.09
    복
    -0.08
    _of
    -0.08
     drove
    -0.07
     STATES
    -0.07
    妥善
    -0.07
    聚集
    -0.07
    Driven
    -0.07
    쮮
    -0.07
    POSITIVE LOGITS
     term
    0.09
     terms
    0.09
    (term
    0.09
    ]-'
    0.07
     scalar
    0.07
     &
    0.07
    		    		
    0.07
     jed
    0.07
     terminals
    0.07
     deterministic
    0.07
    Activations Density 0.053%

    No Known Activations