INDEX

Explanations

reserve

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EXT

-0.26

qui

-0.24

wart

-0.24

 ÑĢÐ°ÑģÐ¿ÑĢ

-0.24

 vite

-0.24

Frm

-0.23

 vehement

-0.23

ATED

-0.23

EXT

-0.23

 Incorrect

-0.23

POSITIVE LOGITS

ingu

0.25

inson

0.25

erson

0.25

æĲģ

0.25

ÑĢÐ°Ð´

0.24

 ourselves

0.24

Ð¾ÑĩÐºÐ¸

0.24

à¦Ľ

0.24

sing

0.24

çĽĶ

0.24

Activations Density 43.292%

reserve

No Comments

No Known Activations