© 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. 19-RESID-POST-AA
    11. 69490
    Prev
    Next
    INDEX
    Explanations

    Calcium concentration in cells

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Us
    -0.08
     �
    -0.07
    .Windows
    -0.07
     inputValue
    -0.07
     Tu
    -0.07
     ∧
    -0.07
    /es
    -0.07
     htmlFor
    -0.07
    火灾
    -0.07
    Tel
    -0.06
    POSITIVE LOGITS
    )";↵
    0.08
    精湛
    0.07
     Preview
    0.07
    rides
    0.07
    /database
    0.07
    urette
    0.07
    -rate
    0.07
     moderation
    0.07
    astery
    0.07
    റ
    0.07
    Activations Density 0.030%

    No Known Activations