INDEX

Explanations

Physical attributes/composition

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

%p

-0.30

LS

-0.25

MISS

-0.25

 ”↵↵

-0.25

(pad

-0.25

åĲĳä¸ľ

-0.25

 Äĳ

-0.24

kÃ¼

-0.24

 Cosby

-0.24

æµĶ

-0.24

POSITIVE LOGITS

 surpassed

0.29

Ĩµ

0.26

å¿ĥè¡Ģ

0.25

 trainable

0.25

å°¤åħ¶æĺ¯åľ¨

0.25

AlgorithmException

0.25

 promot

0.24

ankan

0.24

éĢļ

0.24

lush

0.24

Activations Density 0.080%

Physical attributes/composition

No Comments

No Known Activations