INDEX

Explanations

secretion

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ±²

-0.28

æĮĩçĤ¹

-0.26

digits

-0.26

æĢİä¹Īè¯´

-0.26

tab

-0.26

PI

-0.25

 coff

-0.25

iran

-0.25

emet

-0.25

istan

-0.24

POSITIVE LOGITS

ssize

0.31

éķ¿çº¦

0.28

çŃ¾çº¦

0.26

ocator

0.26

èĭĮ

0.26

 Ã§Ä±kar

0.25

tml

0.25

_EOL

0.25

STM

0.25

OptionsMenu

0.24

Activations Density 0.054%

secretion

No Comments

No Known Activations