INDEX

Explanations

energy/calories

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĢĽ

-0.29

èĳĹåĲįçļĦ

-0.28

ieval

-0.27

æĿ³

-0.26

>Create

-0.26

èĳĹåĲį

-0.26

åĪĨæĺİ

-0.25

æ¶¦æ»ĳ

-0.25

çŀ¿

-0.25

æ³¾

-0.24

POSITIVE LOGITS

hiro

0.28

evenodd

0.27

avor

0.27

 remain

0.26

 hÆ¡i

0.25

Rem

0.25

ACES

0.24

REM

0.24

it

0.24

å¤ļé¡¹

0.24

Activations Density 1.117%

energy/calories

No Comments

No Known Activations