© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8661
    Prev
    Next
    INDEX
    Explanations

    markup

    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
     fluffy
    -0.08
    BLE
    -0.07
     Meteor
    -0.07
    月亮
    -0.07
    Ren
    -0.07
    收获
    -0.07
    室外
    -0.07
     oat
    -0.07
     CCT
    -0.07
    Beth
    -0.07
    POSITIVE LOGITS
    (['/
    0.07
     capitalist
    0.07
     fullPath
    0.07
    VMLINUX
    0.07
    いくら
    0.07
     FormControl
    0.07
    泜
    0.07
    ❰
    0.06
    osphate
    0.06
     capitalize
    0.06
    Activations Density 0.002%

    No Known Activations