INDEX

Explanations

-

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Extras

-0.29

 Extras

-0.26

 staff

-0.25

"\↵

-0.25

extras

-0.25

AGMA

-0.25

amientos

-0.25

åĬ³

-0.24

"+↵

-0.24

çĸĨ

-0.24

POSITIVE LOGITS

è¿Ļä¸¤ä¸ª

0.35

çļĦæĹ¥

0.28

ä¾Ľ

0.27

ople

0.27

obuf

0.25

ropy

0.25

.onCreate

0.25

è¯¾

0.24

ãģĿãĤĮãģŀãĤĮ

0.24

toi

0.24

Activations Density 0.001%

-

No Comments

No Known Activations