INDEX

Explanations

computers/technology

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

ctions

-0.27

 ÑģÑĭ

-0.26

èĥ½åĬĽåĴĮ

-0.26

.isVisible

-0.25

cies

-0.25

reich

-0.25

ä¼¯

-0.24

nge

-0.24

å¿ħ

-0.24

iser

-0.24

POSITIVE LOGITS

ç¼º

0.30

inn

0.27

irr

0.26

ilet

0.26

 sÃ³c

0.25

ption

0.25

acco

0.24

wa

0.24

abstract

0.23

æ´»

0.23

Activations Density 0.785%

computers/technology

No Comments

No Known Activations