INDEX

Explanations

delays

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

è¶ĭåĬ¿

-0.29

 Copp

-0.26

çĽ´

-0.26

SSIP

-0.25

 doubtful

-0.25

èĩªå¸¦

-0.25

obel

-0.24

ters

-0.24

ev

-0.24

 conv

-0.24

POSITIVE LOGITS

perienced

0.27

çļĦåıĳçĶŁ

0.25

åĽŀäºĭ

0.25

Ð»ÐµÑĩ

0.25

imp

0.25

clinic

0.25

loquent

0.24

 clinic

0.24

 formal

0.24

åĩĢåľŁ

0.23

Activations Density 0.556%

delays

No Comments

No Known Activations