INDEX

Explanations

traveling

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tamp

-0.27

èĬĤ

-0.26

bc

-0.26

éĩįå¤§

-0.26

æĦıåĽ¾

-0.25

ester

-0.25

BC

-0.25

æķĻä¼ļ

-0.25

åĨ²

-0.25

 Stim

-0.25

POSITIVE LOGITS

äºı

0.26

 LogLevel

0.26

itr

0.25

/moment

0.25

ToDevice

0.25

cep

0.24

 companyId

0.24

 concentrated

0.23

 recognised

0.23

amps

0.23

Activations Density 45.158%

traveling

No Comments

No Known Activations