INDEX

Explanations

tool

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

 carte

-0.25

å²Ļ

-0.25

iola

-0.25

Stretch

-0.24

Extended

-0.24

 McCart

-0.24

 Huffman

-0.24

 Stretch

-0.24

 overst

-0.24

abis

-0.23

POSITIVE LOGITS

dings

0.27

åį´è¢«

0.24

 Vern

0.24

ercul

0.24

ickers

0.24

icates

0.24

-going

0.24

 pleasing

0.24

 travel

0.23

tps

0.23

Activations Density 0.013%

tool

No Comments

No Known Activations