© 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
    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. 8900
    Prev
    Next
    INDEX
    Explanations

    MAX

    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
     simples
    -0.07
    ajs
    -0.07
    ariant
    -0.07
     år
    -0.07
     partir
    -0.06
    ṫ
    -0.06
     следует
    -0.06
     форум
    -0.06
    唢
    -0.06
    emble
    -0.06
    POSITIVE LOGITS
    _Status
    0.07
    财物
    0.07
    _rgba
    0.07
    	from
    0.07
    signup
    0.07
     NGX
    0.07
     Glob
    0.06
     fetch
    0.06
     delaying
    0.06
    静
    0.06
    Activations Density 0.005%

    No Known Activations