INDEX

Explanations

enzymes and computer terms

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

çĶŁçĶŁ

-0.26

á»©

-0.25

åįĬå¤©

-0.24

åİ»æī¾

-0.24

-nil

-0.23

:return

-0.23

aida

-0.23

;break

-0.23

-fr

-0.23

èĩªæ²»

-0.23

POSITIVE LOGITS

 Dise

0.25

æĹ¨

0.25

Ĳľ

0.24

 Designs

0.24

tou

0.24

alten

0.24

 backs

0.24

reat

0.24

éªĬ

0.23

urpose

0.23

Activations Density 0.023%

enzymes and computer terms

No Comments

No Known Activations