INDEX

Explanations

Mr and period

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ãĤ¢ãĥ¼

-0.26

beck

-0.26

eron

-0.26

LOS

-0.25

azines

-0.25

 Raised

-0.25

DON

-0.25

ç¤¼æĭľ

-0.25

è¾Ī

-0.24

ert

-0.24

POSITIVE LOGITS

legg

0.31

(($

0.27

å¹²ä»Ģä¹Ī

0.26

(TM

0.25

ool

0.25

 langu

0.25

æľīä¿¡å¿ĥ

0.25

(dispatch

0.24

(nil

0.24

(tm

0.24

Activations Density 0.010%

Mr and period

No Comments

No Known Activations