INDEX

Explanations

ophysical

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

ä»µ

-0.28

CR

-0.26

 Carry

-0.26

èĳĹ

-0.26

etter

-0.26

åĬĽ

-0.26

åį³

-0.25

rup

-0.25

çĿĢ

-0.25

 thá»©c

-0.25

POSITIVE LOGITS

cej

0.26

 znaj

0.25

 LOSS

0.25

è¯įæĿ¡

0.25

oble

0.25

trl

0.25

useRalativeImagePath

0.25

 euler

0.24

ollection

0.24

golden

0.24

Activations Density 0.019%

ophysical

No Comments

No Known Activations