INDEX

Explanations

6

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

·æĸ°

-0.28

rices

-0.28

iam

-0.27

hes

-0.25

ç¥ī

-0.25

ill

-0.25

Data

-0.24

æľŁ

-0.24

Im

-0.24

è¯´èµ·

-0.24

POSITIVE LOGITS

bose

0.30

å¹²çº¿

0.26

VERT

0.25

ä¸ĵè®¿

0.24

é¾Ł

0.24

ä¹°çļĦ

0.23

 Trail

0.23

atform

0.23

“(

0.23

ç¨ł

0.23

Activations Density 0.020%

6

No Comments

No Known Activations