© 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. 19-RESID-POST-AA
    6. 3130
    Prev
    Next
    INDEX
    Explanations

    which

    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
    WebService
    -0.08
    🎥
    -0.07
    שירות
    -0.07
    ◓
    -0.07
    ruptcy
    -0.07
    Drug
    -0.07
     Prostit
    -0.07
    美味し
    -0.07
     In
    -0.07
    (Sprite
    -0.06
    POSITIVE LOGITS
     None
    0.07
    >$
    0.07
    							   
    0.07
    buff
    0.07
    .Box
    0.07
    _ITER
    0.07
    				   
    0.07
    <div
    0.07
    кер
    0.07
    DF
    0.06
    Activations Density 0.020%

    No Known Activations