Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43908
    Prev
    Next
    INDEX
    Explanations

    The

    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
     rút
    -0.07
    Ƞ
    -0.07
    かり
    -0.07
    𓂃
    -0.07
    注销
    -0.07
    :UIControlStateNormal
    -0.07
    辦理
    -0.07
    ӏ
    -0.07
    iaux
    -0.07
     disrupting
    -0.07
    POSITIVE LOGITS
    datal
    0.07
    atif
    0.07
    _taken
    0.07
    틀
    0.07
    	Debug
    0.07
    _soup
    0.07
     방법
    0.07
     Implements
    0.07
    SEQU
    0.06
    Artifact
    0.06
    Activations Density 0.034%

    No Known Activations