© 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 EvalsExportsinterp-engineNEWAPI 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. 7464
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    _BASIC
    -0.07
     sach
    -0.07
    argar
    -0.07
    zu
    -0.06
    كثر
    -0.06
     Lan
    -0.06
    ものを
    -0.06
     kan
    -0.06
    นำเสนอ
    -0.06
    Sum
    -0.06
    POSITIVE LOGITS
    拇
    0.07
    خارج
    0.07
    coins
    0.07
    庙
    0.07
    _ent
    0.07
    ◠
    0.06
     curiosity
    0.06
    Restaurant
    0.06
     |_|
    0.06
    驿
    0.06
    Activations Density 0.221%

    No Known Activations