© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6550
    Prev
    Next
    INDEX
    Explanations

    Toxicity/Safety

    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
    ュ
    -0.08
    不敢
    -0.08
    _plugins
    -0.08
     finally
    -0.07
    说不定
    -0.07
    パパ
    -0.07
    終於
    -0.07
     MILF
    -0.07
    awi
    -0.07
     thực
    -0.07
    POSITIVE LOGITS
    (scores
    0.07
     Masters
    0.07
     Hale
    0.07
    _bug
    0.07
    Americ
    0.07
    #\
    0.07
    جماع
    0.07
    	size
    0.06
    riangle
    0.06
    位居
    0.06
    Activations Density 0.072%

    No Known Activations