INDEX

Explanations

name

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

 Submitted

-0.25

essim

-0.25

_TYPED

-0.25

å²ģä»¥ä¸Ĭ

-0.25

 ordin

-0.25

submitted

-0.24

ç§ĺä¹¦éķ¿

-0.24

æ´Ĺæīĭ

-0.24

gemÃ¤ÃŁ

-0.24

(suite

-0.23

POSITIVE LOGITS

 Phar

0.27

ãĥ¼ãĤ·

0.27

Occ

0.27

 spar

0.27

è¾į

0.26

à¹ĩà¸Ļ

0.26

èĬĤçĽ®ä¸Ń

0.26

Occ

0.25

èī¯

0.25

piv

0.25

Activations Density 0.001%

name

No Comments

No Known Activations