INDEX

Explanations

quotations and legal documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ophobic

-0.26

çªĦ

-0.25

å¤´åıĳ

-0.25

è¡¨åĨ³

-0.25

(lib

-0.25

 alike

-0.25

èĵ¼

-0.25

 carrier

-0.24

è·ª

-0.24

heed

-0.24

POSITIVE LOGITS

ILER

0.30

 Pods

0.28

ä¸Ģå¹´ä¸Ģåº¦

0.27

@class

0.26

IGH

0.26

swick

0.26

 transformers

0.25

edom

0.25

 getModel

0.24

Screens

0.24

Activations Density 0.012%

quotations and legal documents

No Comments

No Known Activations