INDEX

Explanations

operation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enger

-0.26

onde

-0.25

æ°¸ä¸į

-0.25

Exact

-0.25

è¿Ļä¸Ģå¹´

-0.24

setType

-0.24

Boost

-0.24

-cent

-0.23

ator

-0.23

 test

-0.23

POSITIVE LOGITS

zsche

0.31

åİĭ

0.27

å¹¸

0.27

EI

0.26

èĬĥ

0.26

pressive

0.25

ÉĲ

0.25

åĳĽ

0.25

áº¯n

0.24

lse

0.24

Activations Density 0.003%

operation

No Comments

No Known Activations