INDEX

Explanations

RIC

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

 Ð´Ð²Ð¾ÑĢ

-0.28

enance

-0.27

URING

-0.27

 weighed

-0.26

werp

-0.26

 nhuáºŃn

-0.25

è°Ł

-0.25

å¶·

-0.25

èłķ

-0.24

oble

-0.24

POSITIVE LOGITS

 Inherits

0.29

ç²³

0.27

ann

0.27

 geÃ§miÅŁ

0.26

ç¼ħ

0.25

æĻļ

0.25

è¿Ľåħ¥äºĨ

0.25

.Support

0.24

æľĿéĺ³

0.24

ä»·ä½į

0.24

Activations Density 0.014%

RIC

No Comments

No Known Activations