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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8618
    Prev
    Next
    INDEX
    Explanations

    sun

    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
     –
    -0.08
    _mapping
    -0.08
    庐
    -0.08
    阵地
    -0.07
     anch
    -0.07
    	store
    -0.07
     prick
    -0.07
    훓
    -0.07
     halt
    -0.07
    Mocks
    -0.07
    POSITIVE LOGITS
     Sun
    0.08
     initWith
    0.07
     X
    0.07
    ########################################################
    0.07
    Ŋ
    0.07
    🙄
    0.06
    的是
    0.06
    剥
    0.06
    cntl
    0.06
    恿
    0.06
    Activations Density 0.028%

    No Known Activations