© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 475
    Prev
    Next
    INDEX
    Explanations

    done

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mpjes
    -0.07
    -loaded
    -0.07
    column
    -0.07
     encuentra
    -0.07
     создан
    -0.07
     trimmed
    -0.07
     knocking
    -0.06
    位列
    -0.06
    𝐚
    -0.06
    aises
    -0.06
    POSITIVE LOGITS
    .performance
    0.07
     Chief
    0.07
     Hero
    0.06
     Dro
    0.06
    ociety
    0.06
     Java
    0.06
     RBI
    0.06
     permits
    0.06
    	emit
    0.06
    <len
    0.06
    Activations Density 0.186%

    No Known Activations