INDEX

Explanations

temper

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

neg

-0.29

ponent

-0.27

å¾Ģä¸Ĭ

-0.26

NEG

-0.26

.addData

-0.26

å¢ŀåĢ¼

-0.25

éĸĵãģ«

-0.25

neg

-0.25

é«ĺä¸ŃçĶŁ

-0.25

 seab

-0.25

POSITIVE LOGITS

legate

0.27

Until

0.27

çĽ´èĩ³

0.26

ural

0.26

çĽ´åĪ°

0.26

acin

0.25

_TUN

0.25

haul

0.24

 Until

0.24

urre

0.24

Activations Density 0.023%

temper

No Comments

No Known Activations