INDEX

Explanations

network

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

æĬķ

-0.30

Ð¸ÑĢÐ¾Ð²ÐºÐ°

-0.27

çļĦåĽŀçŃĶ

-0.25

decision

-0.25

Wnd

-0.24

quals

-0.24

ãĥ©ãĥ³

-0.24

idot

-0.24

æ´¾

-0.24

äº§

-0.23

POSITIVE LOGITS

 contests

0.29

igham

0.29

uffy

0.28

dm

0.28

 folds

0.26

yth

0.25

 Competition

0.25

 edits

0.24

JsonProperty

0.24

é¥±

0.24

Activations Density 0.835%

network

No Comments

No Known Activations